Tootfinder

MAPF-World: Action World Model for Multi-Agent Path Finding
Zhanjiang Yang, Meng Li, Yang Shen, Yueming Li, Lijun Sun
https://arxiv.org/abs/2508.12087 https://

MAPF-World: Action World Model for Multi-Agent Path Finding
Multi-agent path finding (MAPF) is the problem of planning conflict-free paths from the designated start locations to goal positions for multiple agents. It underlies a variety of real-world tasks, including multi-robot coordination, robot-assisted logistics, and social navigation. Recent decentralized learnable solvers have shown great promise for large-scale MAPF, especially when leveraging foundation models and large datasets. However, these agents are reactive policy models and exhibit limi…

"The understanding that the total supremacy of the “data” discourse was always a problematic, neoliberal way of seeing and structuring the world, of legitimizing violence according to the needs of those in power."
(Original title: The “Data” Narrative eats itself)
https://tante.cc/2025/09/15/…

The "Data" Narrative eats itself
“The first model fakes the data, then the second model trains on the fake data. Any problems in the synthetic data set are amplified further. Then the second model — based on fake data — is used to treat real patients. This is, of course, all fine.” Today I want to take David Gerard’s recent […]

Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
Arian Mousakhan, Sudhanshu Mittal, Silvio Galesso, Karim Farid, Thomas Brox
https://arxiv.org/abs/2507.13162

Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
Existing world models for autonomous driving struggle with long-horizon generation and generalization to challenging scenarios. In this work, we develop a model using simple design choices, and without additional supervision or sensors, such as maps, depth, or multiple cameras. We show that our model yields state-of-the-art performance, despite having only 469M parameters and being trained on 280h of video data. It particularly stands out in difficult scenarios like turning maneuvers and urban …

Leveraging Large Language Models for Predictive Analysis of Human Misery
Bishanka Seal, Rahul Seetharaman, Aman Bansal, Abhilash Nandy
https://arxiv.org/abs/2508.12669 https://

Leveraging Large Language Models for Predictive Analysis of Human Misery
This study investigates the use of Large Language Models (LLMs) for predicting human-perceived misery scores from natural language descriptions of real-world scenarios. The task is framed as a regression problem, where the model assigns a scalar value from 0 to 100 to each input statement. We evaluate multiple prompting strategies, including zero-shot, fixed-context few-shot, and retrieval-based prompting using BERT sentence embeddings. Few-shot approaches consistently outperform zero-shot base…

I have to agree with Hofmann, LSD really lets you connect with nature in a way that’s unlike anything else. It’s not just seeing trees or animals differently, it’s like the walls between you and the world around you come down, and you feel everything’s alive and connected.
That experience makes it impossible to ignore how fragile and important all of this is, the plants, animals, the earth itself, and us too. It’s a reminder that we’re part of something bigger, and that caring for natu…

Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
Yu Ge (Nanjing University), Linna Xie (Nanjing University), Zhong Li (Nanjing University), Yu Pei (The Hong Kong Polytechnic University), Tian Zhang (Nanjing University)
https://arxiv.org/abs/2509.13782

Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis
Large Language Model Powered Multi-Agent Systems (MASs) are increasingly employed to automate complex real-world problems, such as programming and scientific discovery. Despite their promising, MASs are not without their flaws. However, failure attribution in MASs - pinpointing the specific agent actions responsible for failures - remains underexplored and labor-intensive, posing significant challenges for debugging and system improvement. To bridge this gap, we propose FAMAS, the first spectru…

A Domain Knowledge Informed Approach for Anomaly Detection of Electric Vehicle Interior Sounds
Deepti Kunte, Bram Cornelis, Claudio Colangeli, Karl Janssens, Brecht Van Baelen, Konstantinos Gryllias
https://arxiv.org/abs/2509.13390

A Domain Knowledge Informed Approach for Anomaly Detection of Electric Vehicle Interior Sounds
The detection of anomalies in automotive cabin sounds is critical for ensuring vehicle quality and maintaining passenger comfort. In many real-world settings, this task is more appropriately framed as an unsupervised learning problem rather than the supervised case due to the scarcity or complete absence of labeled faulty data. In such an unsupervised setting, the model is trained exclusively on healthy samples and detects anomalies as deviations from normal behavior. However, in the absence of…

Control of Legged Robots using Model Predictive Optimized Path Integral
Hossein Keshavarz, Alejandro Ramirez-Serrano, Majid Khadiv
https://arxiv.org/abs/2508.11917 https://

Control of Legged Robots using Model Predictive Optimized Path Integral
Legged robots possess a unique ability to traverse rough terrains and navigate cluttered environments, making them well-suited for complex, real-world unstructured scenarios. However, such robots have not yet achieved the same level as seen in natural systems. Recently, sampling-based predictive controllers have demonstrated particularly promising results. This paper investigates a sampling-based model predictive strategy combining model predictive path integral (MPPI) with cross-entropy (CE) a…

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
Bingshen Mu, Pengcheng Guo, Zhaokai Sun, Shuai Wang, Hexin Liu, Mingchen Shao, Lei Xie, Eng Siong Chng, Longshuai Xiao, Qiangze Feng, Daliang Wang
https://arxiv.org/abs/2509.13785

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
This paper summarizes the Interspeech2025 Multilingual Conversational Speech Language Model (MLC-SLM) challenge, which aims to advance the exploration of building effective multilingual conversational speech LLMs (SLLMs). We provide a detailed description of the task settings for the MLC-SLM challenge, the released real-world multilingual conversational speech dataset totaling approximately 1,604 hours, and the baseline systems for participants. The MLC-SLM challenge attracts 78 teams from 13 c…

Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
Zhixion Chen, Jiangzhou Wang, and Hyundong Shin, Arumugam Nallanathan
https://arxiv.org/abs/2509.13934

Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
The deployment of unmanned aerial vehicles (UAVs) for reliable and energy-efficient data collection from spatially distributed devices holds great promise in supporting diverse Internet of Things (IoT) applications. Nevertheless, the limited endurance and communication range of UAVs necessitate intelligent trajectory planning. While reinforcement learning (RL) has been extensively explored for UAV trajectory optimization, its interactive nature entails high costs and risks in real-world environ…

A Large-Scale Web Search Dataset for Federated Online Learning to Rank
Marcel Gregoriadis, Jingwei Kang, Johan Pouwelse
https://arxiv.org/abs/2508.12353 https://

A Large-Scale Web Search Dataset for Federated Online Learning to Rank
The centralized collection of search interaction logs for training ranking models raises significant privacy concerns. Federated Online Learning to Rank (FOLTR) offers a privacy-preserving alternative by enabling collaborative model training without sharing raw user data. However, benchmarks in FOLTR are largely based on random partitioning of classical learning-to-rank datasets, simulated user clicks, and the assumption of synchronous client participation. This oversimplifies real-world dynami…

A Neuromorphic Model of Learning Meaningful Sequences with Long-Term Memory
Laxmi R. Iyer, Ali A. Minai
https://arxiv.org/abs/2509.12850 https://arxiv.org/…

A Neuromorphic Model of Learning Meaningful Sequences with Long-Term Memory
Learning meaningful sentences is different from learning a random set of words. When humans understand the meaning, the learning occurs relatively quickly. What mechanisms enable this to happen? In this paper, we examine the learning of novel sequences in familiar situations. We embed the Small World of Words (SWOW-EN), a Word Association Norms (WAN) dataset, in a spiking neural network based on the Hierarchical Temporal Memory (HTM) model to simulate long-term memory. Results show that in the …

A General Model for Static Contact Angles
Carlos E Colosqui
https://arxiv.org/abs/2509.14692 https://arxiv.org/pdf/2509.14692

A General Model for Static Contact Angles
The problem of contact angle and hysteresis determination has direct implications for engineering applications of wetting, colloid and surface science. Significant technical challenges can arise under real-world operating conditions, because the static contact angle is strongly influenced by contamination at the liquid-solid and liquid-vapor interfaces, chemical aging over long times, and environmental variables such as relative humidity and temperature. Analytical models that account for these…

Hyperspectral Polarimetric BRDFs of Real-world Materials
Yunseong Moon, Ryota Maeda, Suhyun Shin, Inseung Hwang, Youngchan Kim, Min H. Kim, Seung-Hwan Baek
https://arxiv.org/abs/2509.13779

Hyperspectral Polarimetric BRDFs of Real-world Materials
Acquiring bidirectional reflectance distribution functions (BRDFs) is essential for simulating light transport and analytically modeling material properties. Over the past two decades, numerous intensity-only BRDF datasets in the visible spectrum have been introduced, primarily for RGB image rendering applications. However, in scientific and engineering domains, there remains an unmet need to model light transport with polarization--a fundamental wave property of light--across hyperspectral ban…

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
Zhuoxuan Zhang, Jinhao Duan, Edward Kim, Kaidi Xu
https://arxiv.org/abs/2509.13664 https://

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal representations of LLMs and can be both detected and controlled at the neuron level. During the model's pre-filling stage, we identify that a small number of neurons, as few as one, encode question ambiguity information. Probes trained on these Ambiguity-Encoding …

When higher-order interactions enhance synchronization: the case of the Kuramoto model
Riccardo Muolo, Hiroya Nakao, Marco Coraggio
https://arxiv.org/abs/2508.10992 https://

When higher-order interactions enhance synchronization: the case of the Kuramoto model
Synchronization is a fundamental phenomenon in complex systems, observed across a wide range of natural and engineered contexts. The Kuramoto model provides a foundational framework for understanding synchronization among coupled oscillators, traditionally assuming pairwise interactions. However, many real-world systems exhibit group and many-body interactions, which can be effectively modeled through hypergraphs. Previous studies suggest that higher-order interactions shrink the attraction bas…

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Senqiao Yang, Junyi Li, Xin Lai, Bei Yu, Hengshuang Zhao, Jiaya Jia
https://arxiv.org/abs/2507.13348

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the performance drops significantly in a small subset of OCR-related tasks, models still perform accurately in most other general VQA tasks with only 1/4 resolution. Therefore, we propose to dynamically proc…

A Pressure-Based Diffusion Model for Influence Maximization on Social Networks
Curt Stutsman, Eliot W. Robson, Abhishek K. Umrawal
https://arxiv.org/abs/2509.12822 https://

A Pressure-Based Diffusion Model for Influence Maximization on Social Networks
In many real-world scenarios, an individual's local social network carries significant influence over the opinions they form and subsequently propagate to others. In this paper, we propose a novel diffusion model -- the Pressure Threshold model (PT) -- for dynamically simulating the spread of influence through a social network. This new model extends the popular Linear Threshold Model (LT) by adjusting a node's outgoing influence proportional to the influence it receives from its activated neig…

A look at the Chile-led Latam-GPT project, which involves 30 Latin American and Caribbean institutions collaborating to release an open-source LLM in September (Cristišn Vera-Cruz/Rest of World)
https://restofworld.org/2025/chatgpt-latin-america-alternative-latamgpt…

Fed up with ChatGPT, Latin America is building its own
Dozens of organizations in the region have partnered to develop a large language model that better understands Latin America’s cultural and linguistic nuances.

Probabilities in Toy Regge models with odderons
M. A. Braun
https://arxiv.org/abs/2509.12819 https://arxiv.org/pdf/2509.12819

Probabilities in Toy Regge models with odderons
The possibi;lity of a probabilistic interpretation is studied for the Regge-Gribov model in zero dimensional transverse world ("Toy") with interacting pomerons and odderons. It is found that the previously proposed recipe to introduce such interpretation in the model without odderons, does not work once odderons are included. Starting from the physically reasonable probabilites it leads to a pathological field theory violating $C$-parity invariance. Inversely, starting from an admissible field …

Just read this post by @… on an optimistic AGI future, and while it had some interesting and worthwhile ideas, it's also in my opinion dangerously misguided, and plays into the current AGI hype in a harmful way.
https://social.coop/@eloquence/114940607434005478
My criticisms include:
- Current LLM technology has many layers, but the biggest most capable models are all tied to corporate datacenters and require inordinate amounts of every and water use to run. Trying to use these tools to bring about a post-scarcity economy will burn up the planet. We urgently need more-capable but also vastly more efficient AI technologies if we want to use AI for a post-scarcity economy, and we are *not* nearly on the verge of this despite what the big companies pushing LLMs want us to think.
- I can see that permacommons.org claims a small level of expenses on AI equates to low climate impact. However, given current deep subsidies on place by the big companies to attract users, that isn't a great assumption. The fact that their FAQ dodges the question about which AI systems they use isn't a great look.
- These systems are not free in the same way that Wikipedia or open-source software is. To run your own model you need a data harvesting & cleaning operation that costs millions of dollars minimum, and then you need millions of dollars worth of storage & compute to train & host the models. Right now, big corporations are trying to compete for market share by heavily subsidizing these things, but it you go along with that, you become dependent on them, and you'll be screwed when they jack up the price to a profitable level later. I'd love to see open dataset initiatives SBD the like, and there are some of these things, but not enough yet, and many of the initiatives focus on one problem while ignoring others (fine for research but not the basis for a society yet).
- Between the environmental impacts, the horrible labor conditions and undercompensation of data workers who filter the big datasets, and the impacts of both AI scrapers and AI commons pollution, the developers of the most popular & effective LLMs have a lot of answer for. This project only really mentions environmental impacts, which makes me think that they're not serious about ethics, which in turn makes me distrustful of the whole enterprise.
- Their language also ends up encouraging AI use broadly while totally ignoring several entire classes of harm, so they're effectively contributing to AI hype, especially with such casual talk of AGI and robotics as if embodied AGI were just around the corner. To be clear about this point: we are several breakthroughs away from AGI under the most optimistic assumptions, and giving the impression that those will happen soon plays directly into the hands of the Sam Altmans of the world who are trying to make money off the impression of impending huge advances in AI capabilities. Adding to the AI hype is irresponsible.
- I've got a more philosophical criticism that I'll post about separately.
I do think that the idea of using AI & other software tools, possibly along with robotics and funded by many local cooperatives, in order to make businesses obsolete before they can do the same to all workers, is a good one. Get your local library to buy a knitting machine alongside their 3D printer.
Lately I've felt too busy criticizing AI to really sit down and think about what I do want the future to look like, even though I'm a big proponent of positive visions for the future as a force multiplier for criticism, and this article is inspiring to me in that regard, even if the specific project doesn't seem like a good one.

Valuation of Exotic Options and Counterparty Games Based on Conditional Diffusion
Helin Zhao, Junchi Shen
https://arxiv.org/abs/2509.13374 https://arxiv.or…

Valuation of Exotic Options and Counterparty Games Based on Conditional Diffusion
This paper addresses the challenges of pricing exotic options and structured products, which traditional models often fail to handle due to their inability to capture real-world market phenomena like fat-tailed distributions and volatility clustering. We introduce a Diffusion-Conditional Probability Model (DDPM) to generate more realistic price paths. Our method incorporates a composite loss function with financial-specific features, and we propose a P-Q dynamic game framework for evaluating th…

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
Heyang Xue, Xuchen Song, Yu Tang, Jianyu Chen, Yanru Chen, Yang Li, Yahui Zhou
https://arxiv.org/abs/2508.11326

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
Description-based text-to-speech (TTS) models exhibit strong performance on in-domain text descriptions, i.e., those encountered during training. However, in real-world applications, the diverse range of user-generated descriptions inevitably introduces numerous out-of-domain inputs that challenge the text understanding capabilities of these systems. To address this issue, we propose MoE-TTS, a description-based TTS model designed to enhance the understanding of out-of-domain text descriptions.…

Empowering Multi-Robot Cooperation via Sequential World Models
Zijie Zhao, Honglei Guo, Shengqian Chen, Kaixuan Xu, Bo Jiang, Yuanheng Zhu, Dongbin Zhao
https://arxiv.org/abs/2509.13095

Empowering Multi-Robot Cooperation via Sequential World Models
Model-based reinforcement learning (MBRL) has shown significant potential in robotics due to its high sample efficiency and planning capability. However, extending MBRL to multi-robot cooperation remains challenging due to the complexity of joint dynamics. To address this, we propose the Sequential World Model (SeqWM), a novel framework that integrates the sequential paradigm into model-based multi-agent reinforcement learning. SeqWM employs independent, sequentially structured agent-wise world…

Before you spend $59 on that iPhone strap, consider giving the same amount to the World Central Kitchen. They help feed people in a humanitarian crisis around the world.
Many thanks for considering my request.
https://wck.org/

Learning, fast and slow: a two-fold algorithm for data-based model adaptation
Laura Boca de Giuli, Alessio La Bella, Riccardo Scattolini
https://arxiv.org/abs/2507.12187

Learning, fast and slow: a two-fold algorithm for data-based model adaptation
This article addresses the challenge of adapting data-based models over time. We propose a novel two-fold modelling architecture designed to correct plant-model mismatch caused by two types of uncertainty. Out-of-domain uncertainty arises when the system operates under conditions not represented in the initial training dataset, while in-domain uncertainty results from real-world variability and flaws in the model structure or training process. To handle out-of-domain uncertainty, a slow learnin…

CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
Shaoming Duan, Zirui Wang, Chuanyi Liu, Zhibin Zhu, Yuhao Zhang, Peiyi Han, Liang Yan, Zewu Penge
https://arxiv.org/abs/2508.12769

CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description
Recent advances in large language models (LLMs) have significantly improved the accuracy of Text-to-SQL systems. However, a critical challenge remains: the semantic mismatch between natural language questions (NLQs) and their corresponding SQL queries. This issue is exacerbated in large-scale databases, where semantically similar attributes hinder schema linking and semantic drift during SQL generation, ultimately reducing model accuracy. To address these challenges, we introduce CRED-SQL, a fr…

Tokopedia sellers say Tokopedia's strengths have eroded since its TikTok Shop merger in Indonesia, driving thousands of sellers to join rivals, including Toco (Michelle Anindya/Rest of World)
https://restofworld.org/2025/tiktok-indonesia-tokopedia-merger-problems…

TikTok’s messy merger in Indonesia could be a preview of what’s to come in the U.S.
A year after merging with local giant Tokopedia, TikTok’s business model is alienating sellers, forcing many to join rival platforms.

Search for High-Energy Neutrinos From the Sun Using Ten Years of IceCube Data
Abbasi, Ackermann, Adams, Agarwalla, Aguilar, Ahlers, Alameddine, Ali, Amin, Andeen, Arg\"uelles, Ashida, Athanasiadou, Axani, Babu, Bai, Baines-Holmes, V., Barwick, Bash, Basu, Bay, Beatty, Tjus, Behrens, Beise, Bellenghi, Benkel, BenZvi, Berley, Bernardini, Besson, Blaufuss, Bloom, Blot, Bodo, Bontempo, Motzkin, Meneguolo, B\"oser, Botner, B\"ottcher, Braun, Brinson, Brisson-Tsavoussis, Burle…

Search for High-Energy Neutrinos From the Sun Using Ten Years of IceCube Data
In this Letter, we present the results of a search for high-energy neutrinos produced by the annihilation of dark matter particles trapped in the Sun. Using 9.3 and 10.4 years of data from the DeepCore and IceCube neutrino detectors, we establish world-best limits for spin-dependent interactions between dark matter and Standard Model particles for dark matter masses from tens of GeV to tens of TeV. We additionally place constraints on the neutrino background produced by interactions of cosmic r…

MIDOG 2025 Track 2: A Deep Learning Model for Classification of Atypical and Normal Mitotic Figures under Class and Hardness Imbalances
Sujatha Kotte, Vangala Govindakrishnan Saipradeep, Vidushi Walia, Dhandapani Nandagopal, Thomas Joseph, Naveen Sivadasan, Bhagat Singh Lali
https://arxiv.org/abs/2509.10502…

MIDOG 2025 Track 2: A Deep Learning Model for Classification of Atypical and Normal Mitotic Figures under Class and Hardness Imbalances
Motivation: Accurate classification of mitotic figures into normal and atypical types is crucial for tumor prognostication in digital pathology. However, developing robust deep learning models for this task is challenging due to the subtle morphological differences, as well as significant class and hardness imbalances in real-world histopathology datasets. Methods: We propose a novel deep learning approach based on a ResNet backbone with specialized classification heads. Our architecture unique…

State Aware Traffic Generation for Real-Time Network Digital Twins
Enes Koktas, Peter Rost
https://arxiv.org/abs/2509.12860 https://arxiv.org/pdf/2509.1286…

State Aware Traffic Generation for Real-Time Network Digital Twins
Digital twins (DTs) enable smarter, self-optimizing mobile networks, but they rely on a steady supply of real world data. Collecting and transferring complete traces in real time is a significant challenge. We present a compact traffic generator that combines hidden Markov model, capturing the broad rhythms of buffering, streaming and idle periods, with a small feed forward mixture density network that generates realistic payload sizes and inter-arrival times to be fed to the DT. This traffic g…

VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification.
This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated…

VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated into the Vulnerability-Lookup service.

LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
Fengxiao Tang, Huan Li, Ming Zhao, Zongzong Wu, Shisong Peng, Tao Yin
https://arxiv.org/abs/2507.11310

LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
Verifying the credibility of Cyber Threat Intelligence (CTI) is essential for reliable cybersecurity defense. However, traditional approaches typically treat this task as a static classification problem, relying on handcrafted features or isolated deep learning models. These methods often lack the robustness needed to handle incomplete, heterogeneous, or noisy intelligence, and they provide limited transparency in decision-making-factors that reduce their effectiveness in real-world threat envi…

Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation
Brian Shing-Hei Wong, Joshua Mincheol Kim, Sin-Hang Fung, Qing Xiong, Kelvin Fu-Kiu Ao, Junkang Wei, Ran Wang, Dan Michelle Wang, Jingying Zhou, Bo Feng, Alfred Sze-Lok Cheng, Kevin Y. Yip, Stephen Kwok-Wing Tsui, Qin Cao
https://arxiv.o…

Driving Accurate Allergen Prediction with Protein Language Models and Generalization-Focused Evaluation
Allergens, typically proteins capable of triggering adverse immune responses, represent a significant public health challenge. To accurately identify allergen proteins, we introduce Applm (Allergen Prediction with Protein Language Models), a computational framework that leverages the 100-billion parameter xTrimoPGLM protein language model. We show that Applm consistently outperforms seven state-of-the-art methods in a diverse set of tasks that closely resemble difficult real-world scenarios. Th…

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
Danielle Ensign, Henry Sleight, Kyle Fish
https://arxiv.org/abs/2509.04781 https://

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
When given the option, will LLMs choose to leave the conversation (bail)? We investigate this question by giving models the option to bail out of interactions using three different bail methods: a bail tool the model can call, a bail string the model can output, and a bail prompt that asks the model if it wants to leave. On continuations of real world data (Wildchat and ShareGPT), all three of these bail methods find models will bail around 0.28-32\% of the time (depending on the model and bail…

LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization
Zhen-Song Chen, Hong-Wei Ding, Xian-Jia Wang, Witold Pedrycz
https://arxiv.org/abs/2508.11871

LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization
Constrained multi-objective optimization problems (CMOPs) frequently arise in real-world applications where multiple conflicting objectives must be optimized under complex constraints. Existing dual-population two-stage algorithms have shown promise by leveraging infeasible solutions to improve solution quality. However, designing high-performing constrained multi-objective evolutionary algorithms (CMOEAs) remains a challenging task due to the intricacy of algorithmic components. Meanwhile, lar…

Universal self-similarity of hierarchical communities formed through a general self-organizing principle
Shruti Tandon (equal), Nidhi Dilip Sonwane (equal), Tobias Braun, Norbert Marwan, Juergen Kurths, R. I. Sujith
https://arxiv.org/abs/2507.11159

Universal self-similarity of hierarchical communities formed through a general self-organizing principle
Emergence of self-similarity in hierarchical community structures is ubiquitous in complex systems. Yet, there is a dearth of universal quantification and general principles describing the formation of such structures. Here, we discover universality in scaling laws describing self-similar hierarchical community structure in multiple real-world networks including biological, infrastructural, and social networks. We replicate these scaling relations using a phenomenological model, where nodes wit…

Hell or High Water: Evaluating Agentic Recovery from External Failures
Andrew Wang, Sophia Hager, Adi Asija, Daniel Khashabi, Nicholas Andrews
https://arxiv.org/abs/2508.11027 h…

Hell or High Water: Evaluating Agentic Recovery from External Failures
As language model agents are applied to real world problems of increasing complexity, they will be expected to formulate plans across large search spaces. If those plans fail for reasons beyond their control, how well do language agents search for alternative ways to achieve their goals? We devise a specialized agentic planning benchmark to study this question. Each planning problem is solved via combinations of function calls. The agent searches for relevant functions from a set of over four t…

Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection
Yue Zhou, Xinan He, Kaiqing Lin, Bing Fan, Feng Ding, Jinhua Zeng, Bin Li
https://arxiv.org/abs/2509.12995

Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection
While specialized detectors for AI-generated images excel on curated benchmarks, they fail catastrophically in real-world scenarios, as evidenced by their critically high false-negative rates on `in-the-wild' benchmarks. Instead of crafting another specialized `knife' for this problem, we bring a `gun' to the fight: a simple linear classifier on a modern Vision Foundation Model (VFM). Trained on identical data, this baseline decisively `outguns' bespoke detectors, boosting in-the-wild accuracy …

Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic processes
Paul M. Riechers, Thomas J. Elliott
https://arxiv.org/abs/2509.03004 h…

Identifiability and minimality bounds of quantum and post-quantum models of classical stochastic processes
To make sense of the world around us, we develop models, constructed to enable us to replicate, describe, and explain the behaviours we see. Focusing on the broad case of sequences of correlated random variables, i.e., classical stochastic processes, we tackle the question of determining whether or not two different models produce the same observable behavior. This is the problem of identifiability. Curiously, the physics of the model need not correspond to the physics of the observations; rece…

Persuading Agents in Opinion Formation Games
Martin Hoefer, Tim Koglin, Tolga Tel
https://arxiv.org/abs/2509.07520 https://arxiv.org/pdf/2509.07520

Persuading Agents in Opinion Formation Games
Prominent opinion formation models such as the one by Friedkin and Johnsen (FJ) concentrate on the effects of peer pressure on public opinions. In practice, opinion formation is also based on information about the state of the world and persuasion efforts. In this paper, we analyze an approach of Bayesian persuasion in the FJ model. There is an unknown state of the world that influences the preconceptions of n agents. A sender S can (partially) reveal information about the state to all agents. …

A Deep Learning Model of Lightning Stroke Density
Randall Jones II, Joel A. Thornton, Chris J. Wright, Robert Holzworth
https://arxiv.org/abs/2509.10399 https://

A Deep Learning Model of Lightning Stroke Density
Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study develops deep learning-based parameterizations of lightning stroke density using meteorological variables from the ERA and IMERG datasets. Convolutional neural networks (CNNs) with U-Net architectures are trained using World Wide Lightning Location Network (W…

Continuous-Time Distributed Learning for Collective Wisdom Maximization
Luka Bakovi\'c, Giacomo Como, Fabio Fagnani, Anton Proskurnikov, Emma Tegling
https://arxiv.org/abs/2509.11808

Continuous-Time Distributed Learning for Collective Wisdom Maximization
Motivated by the well established idea that collective wisdom is greater than that of an individual, we propose a novel learning dynamics as a sort of companion to the Abelson model of opinion dynamics. Agents are assumed to make independent guesses about the true state of the world after which they engage in opinion exchange leading to consensus. We investigate the problem of finding the optimal parameters for this exchange, e.g. those that minimize the variance of the consensus value. Specifi…

Unsupervised Deep Equilibrium Model Learning for Large-Scale Channel Estimation with Performance Guarantees
Haotian Tian, Lixiang Lian
https://arxiv.org/abs/2508.10546 https://

Unsupervised Deep Equilibrium Model Learning for Large-Scale Channel Estimation with Performance Guarantees
Supervised deep learning methods have shown promise for large-scale channel estimation (LCE), but their reliance on ground-truth channel labels greatly limits their practicality in real-world systems. In this paper, we propose an unsupervised learning framework for LCE that does not require ground-truth channels. The proposed approach leverages Generalized Stein's Unbiased Risk Estimate (GSURE) as a principled unsupervised loss function, which provides an unbiased estimate of the projected mean…

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
Akshit Sinha, Arvindh Arun, Shashwat Goel, Steffen Staab, Jonas Geiping
https://arxiv.org/abs/2509.09677

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
Does continued scaling of large language models (LLMs) yield diminishing returns? Real-world value often stems from the length of task an agent can complete. We start this work by observing the simple but counterintuitive fact that marginal gains in single-step accuracy can compound into exponential improvements in the length of a task a model can successfully complete. Then, we argue that failures of LLMs when simple tasks are made longer arise from mistakes in execution, rather than an inabil…

After training, we finetune on real-world data. We observe that the models that have been pre-trained with noise converge very quickly compared to a baseline which is trained from scratch.
Moreover, on the other datasets, the UP models retain their zero-shot performance during finetuning. This suggests that there may be a generalization benefit to using a UP model.
All this is at the expense of much longer training, but that cost can be amortized over many tasks.

Subtooting since people in the original thread wanted it to be over, but selfishly tagging @… and @… whose opinions I value...
I think that saying "we are not a supply chain" is exactly what open-source maintainers should be doing right now in response to "open source supply chain security" threads.
I can't claim to be an expert and don't maintain any important FOSS stuff, but I do release almost all of my code under open licenses, and I do use many open source libraries, and I have felt the pain of needing to replace an unmaintained library.
There's a certain small-to-mid-scale class of program, including many open-source libraries, which can be built/maintained by a single person, and which to my mind best operate on a "snake growth" model: incremental changes/fixes, punctuated by periodic "skin-shedding" phases where make rewrites or version updates happen. These projects aren't immortal either: as the whole tech landscape around them changes, they become unnecessary and/or people lose interest, so they go unmaintained and eventually break. Each time one of their dependencies breaks (or has a skin-shedding moment) there's a higher probability that they break or shed too, as maintenance needs shoot up at these junctures. Unless you're a company trying to make money from a single long-lived app, it's actually okay that software churns like this, and if you're a company trying to make money, your priorities absolutely should not factor into any decisions people making FOSS software make: we're trying (and to a huge extent succeeding) to make a better world (and/or just have fun with our own hobbies share that fun with others) that leaves behind the corrosive & planet-destroying plague which is capitalism, and you're trying to personally enrich yourself by embracing that plague. The fact that capitalism is *evil* is not an incidental thing in this discussion.
To make an imperfect analogy, imagine that the peasants of some domain have set up a really-free-market, where they provide each other with free stuff to help each other survive, sometimes doing some barter perhaps but mostly just everyone bringing their surplus. Now imagine the lord of the domain, who is the source of these peasants' immiseration, goes to this market secretly & takes some berries, which he uses as one ingredient in delicious tarts that he then sells for profit. But then the berry-bringer stops showing up to the free market, or starts bringing a different kind of fruit, or even ends up bringing rotten berries by accident. And the lord complains "I have a supply chain problem!" Like, fuck off dude! Your problem is that you *didn't* want to build a supply chain and instead thought you would build your profit-focused business in other people's free stuff. If you were paying the berry-picker, you'd have a supply chain problem, but you weren't, so you really have an "I want more free stuff" problem when you can't be arsed to give away your own stuff for free.
There can be all sorts of problems in the really-free-market, like maybe not enough people bring socks, so the peasants who can't afford socks are going barefoot, and having foot problems, and the peasants put their heads together and see if they can convince someone to start bringing socks, and maybe they can't and things are a bit sad, but the really-free-market was never supposed to solve everyone's problems 100% when they're all still being squeezed dry by their taxes: until they are able to get free of the lord & start building a lovely anarchist society, the really-free-market is a best-effort kind of deal that aims to make things better, and sometimes will fall short. When it becomes the main way goods in society are distributed, and when the people who contribute aren't constantly drained by the feudal yoke, at that point the availability of particular goods is a real problem that needs to be solved, but at that point, it's also much easier to solve. And at *no* point does someone coming into the market to take stuff only to turn around and sell it deserve anything from the market or those contributing to it. They are not a supply chain. They're trying to help each other out, but even then they're doing so freely and without obligation. They might discuss amongst themselves how to better coordinate their mutual aid, but they're not going to end up forcing anyone to bring anything or even expecting that a certain person contribute a certain amount, since the whole point is that the thing is voluntary & free, and they've all got changing life circumstances that affect their contributions. Celebrate whatever shows up at the market, express your desire for things that would be useful, but don't impose a burden on anyone else to bring a specific thing, because otherwise it's fair for them to oppose such a burden on you, and now you two are doing your own barter thing that's outside the parameters of the really-free-market.

OnlineHOI: Towards Online Human-Object Interaction Generation and Perception
Yihong Ji, Yunze Liu, Yiyao Zhuo, Weijiang Yu, Fei Ma, Joshua Huang, Fei Yu
https://arxiv.org/abs/2509.12250

OnlineHOI: Towards Online Human-Object Interaction Generation and Perception
The perception and generation of Human-Object Interaction (HOI) are crucial for fields such as robotics, AR/VR, and human behavior understanding. However, current approaches model this task in an offline setting, where information at each time step can be drawn from the entire interaction sequence. In contrast, in real-world scenarios, the information available at each time step comes only from the current moment and historical data, i.e., an online setting. We find that offline methods perform…

On the $Z_q$-forcing number: computational approach and exact values
Aida Abiad, Maryam Moghaddas
https://arxiv.org/abs/2509.03967 https://arxiv.org/pdf/25…

On the $Z_q$-forcing number: computational approach and exact values
Zero forcing is a graph coloring process that is used to model spreading phenomena in real-world scenarios. It can also be viewed as a single-player combinatorial game on a graph, where the player's goal is to select a subset of vertices of minimum cardinality that eventually leads to all vertices of the graph being colored. A variant of this game, called the $q$-analogue of zero forcing, was later introduced. In this version, the player again seeks to choose the smallest number of vertices tha…

The Impact of Different Haze Types on the Atmosphere and Observations of Hot Jupiters: 3D Simulations of HD 189733b, HD209458b and WASP-39b
Mei Ting Mak, Denis Sergeev, Nathan Mayne, Maria Zamyatina, Maria E. Steinrueck, James Manners, Eric Hebrard, David K. Sing, Krisztian Kohary
https://arxiv.org/abs/2507.20366

The Impact of Different Haze Types on the Atmosphere and Observations of Hot Jupiters: 3D Simulations of HD 189733b, HD209458b and WASP-39b
We present the results from the simulations of the atmospheres of hot-Jupiters HD189733b, HD209458b and WASP-39b, assuming the presence of three different types of haze. Using a 3D General Circulation Model, the Unified Model, we capture the advection, settling and radiative impact of Titan-like, water-world-like and soot-like haze, with a particle radius of 1.5 nm. We show that the radiative impact of haze leads to drastic changes in the thermal structure and circulation in the atmosphere. We …

Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Synthesis
Mickael Randour
https://arxiv.org/abs/2509.04129 https://

Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Synthesis
In the game-theoretic approach to controller synthesis, we model the interaction between a system to be controlled and its environment as a game between these entities, and we seek an appropriate (e.g., winning or optimal) strategy for the system. This strategy then serves as a formal blueprint for a real-world controller. A common belief is that simple (e.g., using limited memory) strategies are better: corresponding controllers are easier to conceive and understand, and cheaper to produce and…

Modelling Scenarios for Carbon-aware Geographic Load Shifting of Compute Workloads
Wim Vanderbauwhede
https://arxiv.org/abs/2509.07043 https://arxiv.org/pd…

Modelling Scenarios for Carbon-aware Geographic Load Shifting of Compute Workloads
We present an analytical model to evaluate the reductions in emissions resulting from geographic load shifting. This model is optimistic as it ignores issues of grid capacity, demand and curtailment. In other words, real-world reductions will be smaller than the estimates. However, even with these assumptions, the presented scenarios show that the realistic reductions from carbon-aware geographic load shifting are small, of the order of 5\%. This is not enough to compensate the growth in emissi…

Tesla shareholders will apparently get to vote on whether Tesla should bail out Xai/Twitter.
Do Tesla shareholders want to give Musk more money in return for Tesla owning part of his nazi AI model and his nazi troll site?
We shall see. My guess is yes! Tesla share owners will vote to dilute themselves in return for the chance to bail out the failing Twitter and Grok.
#xai #grok #twitter #tesla

From Paradigm Shift to Audit Rift: Exploring Vulnerabilities and Audit Tips for TON Smart Contracts
Yury Yanovich, Sergey Sobolev, Yash Madhwal, Kirill Ziborov, Vladimir Gorgadze, Victoria Kovalevskay, Elizaveta Smirnova, Matvey Mishuris, Subodh Sharma
https://arxiv.org/abs/2509.10823

From Paradigm Shift to Audit Rift: Exploring Vulnerabilities and Audit Tips for TON Smart Contracts
The Open Network (TON) is a high-performance blockchain platform designed for scalability and efficiency, leveraging an asynchronous execution model and a multi-layered architecture. While TON's design offers significant advantages, it also introduces unique challenges for smart contract development and security. This paper introduces a comprehensive audit checklist for TON smart contracts, based on an analysis of 34 professional audit reports containing 233 real-world vulnerabilities. The chec…

Taming Volatility: Stable and Private QUIC Classification with Federated Learning
Richard Jozsa, Karel Hynek, Adrian Pekar
https://arxiv.org/abs/2509.09997 https://

Taming Volatility: Stable and Private QUIC Classification with Federated Learning
Federated Learning (FL) is a promising approach for privacy-preserving network traffic analysis, but its practical deployment is challenged by the non-IID nature of real-world data. While prior work has addressed statistical heterogeneity, the impact of temporal traffic volatility-the natural daily ebb and flow of network activity-on model stability remains largely unexplored. This volatility can lead to inconsistent data availability at clients, destabilizing the entire training process. In th…

"Draw me a curator" Examining the visual stereotyping of a cultural services profession by generative AI
Dirk HR Spennemann
https://arxiv.org/abs/2508.07132 https://…

"Draw me a curator" Examining the visual stereotyping of a cultural services profession by generative AI
Based on 230 visualisations, this paper examines the depiction of museum curators by the popular generative Artificial Intelligence (AI) model, ChatGPT4o. While the AI-generated representations do not reiterate popular stereotypes of curators as nerdy, conservative in dress and stuck in time rummaging through collections, they contrast sharply with real-world demographics. AI-generated imagery extremely underrepresents women (3.5% vs 49% to 72% in reality) and disregards ethnic communities othe…

How long until the internet, which allowed a generation to benefit from a vast wealth of human knowledge, becomes a swamp filled with generated #AI pollution? It may already be too late. https://www.theregist…

The launch of ChatGPT polluted the world forever, like the first atomic weapons tests
Feature: Academics mull the need for the digital equivalent of low-background steel

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering
Yinsheng Li, Zhen Dong, Yi Shao
https://arxiv.org/abs/2507.11527

DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering
Large Language Model (LLM) agents have shown great potential for solving real-world problems and promise to be a solution for tasks automation in industry. However, more benchmarks are needed to systematically evaluate automation agents from an industrial perspective, for example, in Civil Engineering. Therefore, we propose DrafterBench for the comprehensive evaluation of LLM agents in the context of technical drawing revision, a representation task in civil engineering. DrafterBench contains t…

Enhancing the Scalability of Classical Surrogates for Real-World Quantum Machine Learning Applications
Philip Anton Hernicht, Alona Sakhnenko, Corey O'Meara, Giorgio Cortiana, Jeanette Miriam Lorenz
https://arxiv.org/abs/2508.06131

Enhancing the Scalability of Classical Surrogates for Real-World Quantum Machine Learning Applications
Quantum machine learning (QML) presents potential for early industrial adoption, yet limited access to quantum hardware remains a significant bottleneck for deployment of QML solutions. This work explores the use of classical surrogates to bypass this restriction, which is a technique that allows to build a lightweight classical representation of a (trained) quantum model, enabling to perform inference on entirely classical devices. We reveal prohibiting high computational demand associated wit…

From Who Said What to Who They Are: Modular Training-free Identity-Aware LLM Refinement of Speaker Diarization
Yu-Wen Chen, William Ho, Maxim Topaz, Julia Hirschberg, Zoran Kostic
https://arxiv.org/abs/2509.15082

From Who Said What to Who They Are: Modular Training-free Identity-Aware LLM Refinement of Speaker Diarization
Speaker diarization (SD) struggles in real-world scenarios due to dynamic environments and unknown speaker counts. SD is rarely used alone and is often paired with automatic speech recognition (ASR), but non-modular methods that jointly train on domain-specific data have limited flexibility. Moreover, many applications require true speaker identities rather than SD's pseudo labels. We propose a training-free modular pipeline combining off-the-shelf SD, ASR, and a large language model (LLM) to d…

Robust Detection of Planted Subgraphs in Semi-Random Models
Dor Elimelech, Wasim Huleihel
https://arxiv.org/abs/2508.02158 https://arxiv.org/pdf/2508.02158…

Robust Detection of Planted Subgraphs in Semi-Random Models
Detection of planted subgraphs in Erdös-Rényi random graphs has been extensively studied, leading to a rich body of results characterizing both statistical and computational thresholds. However, most prior work assumes a purely random generative model, making the resulting algorithms potentially fragile in the face of real-world perturbations. In this work, we initiate the study of semi-random models for the planted subgraph detection problem, wherein an adversary is allowed to remove edges o…

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
Yihua Wang, Qi Jia, Cong Xu, Feiyu Chen, Yuhan Liu, Haotian Zhang, Liang Jin, Lu Liu, Zhichun Wang
https://arxiv.org/abs/2508.10644

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm…

A Type 2 Fuzzy Set Approach for Building Linear Linguistic Regression Analysis under Multi Uncertainty
Junzo Watada, Pei-Chun Lin, Bo Wang, Jeng-Shyang Pan, Jose Guadalupe Flores Muniz
https://arxiv.org/abs/2509.10498

A Type 2 Fuzzy Set Approach for Building Linear Linguistic Regression Analysis under Multi Uncertainty
In this paper, we propose a novel heuristic algorithm for constructing a Type-2 Fuzzy Set of the Linear Linguistic Regression (T2F-LLR) model, designed to address uncertainty and vagueness in real-world decision-making. We consider a practical scenario involving a cosmetic company's promotional planning across four product categories: Basic Face Care, Face Cleaning, Cosmetics, and Body Care, aimed at both male and female consumers. Data are collected using fuzzy linguistic questionnaires from c…

Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model
Xu Yang, Rui Wang, Kaiwen Li, Wenhua Li, Ling Wang
https://arxiv.org/abs/2509.11016

Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model
Despite significant efforts to manually design high-performance evolutionary algorithms, their adaptability remains limited due to the dynamic and ever-evolving nature of real-world problems. The "no free lunch" theorem highlights that no single algorithm performs optimally across all problems. While online adaptation methods have been proposed, they often suffer from inefficiency, weak convergence, and limited generalization on constrained optimization problems (COPs). To address these chall…

Emergence of Cooperation and Commitment in Optional Prisoner's Dilemma
Zhao Song, The Anh Han
https://arxiv.org/abs/2508.06702 https://arxiv.org/pdf/25…

Emergence of Cooperation and Commitment in Optional Prisoner's Dilemma
Commitment is a well-established mechanism for fostering cooperation in human society and multi-agent systems. However, existing research has predominantly focused on the commitment that neglects the freedom of players to abstain from an interaction, limiting their applicability to many real-world scenarios where participation is often voluntary. In this paper, we present a two-stage game model to investigate the evolution of commitment-based behaviours and cooperation within the framework of t…

OpenAI says GPT-5 is its first "unified" AI model and combines the reasoning abilities of its o-series of models with the fast responses of its GPT series (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/08/07/openais-gpt-5-is-here/

OpenAI's GPT-5 is here | TechCrunch
OpenAI CEO Sam Altman says GPT-5 is the "best model in the world," and aims to make ChatGPT more intuitive to use.

A Synthetic-to-Real Dehazing Method based on Domain Unification
Zhiqiang Yuan, Jinchao Zhang, Jie Zhou
https://arxiv.org/abs/2509.05374 https://arxiv.org/p…

A Synthetic-to-Real Dehazing Method based on Domain Unification
Due to distribution shift, the performance of deep learning-based method for image dehazing is adversely affected when applied to real-world hazy images. In this paper, we find that such deviation in dehazing task between real and synthetic domains may come from the imperfect collection of clean data. Owing to the complexity of the scene and the effect of depth, the collected clean data cannot strictly meet the ideal conditions, which makes the atmospheric physics model in the real domain incon…

Real-Time Analysis of Unstructured Data with Machine Learning on Heterogeneous Architectures
Fotis I. Giasemis
https://arxiv.org/abs/2508.07423 https://arx…

Real-Time Analysis of Unstructured Data with Machine Learning on Heterogeneous Architectures
As the particle physics community needs higher and higher precisions in order to test our current model of the subatomic world, larger and larger datasets are necessary. With upgrades scheduled for the detectors of colliding-beam experiments around the world, and specifically at the Large Hadron Collider at CERN, more collisions and more complex interactions are expected. This directly implies an increase in data produced and consequently in the computational resources needed to process them. A…

Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
Matej Vitek, Darian Toma\v{s}evi\'c, Abhijit Das, Sabari Nathan, G\"okhan \"Ozbulak, G\"ozde Ay\c{s}e Tataro\u{g}lu \"Ozbulak, Jean-Paul Calbimonte, Andr\'e Anjos, Hariohm Hemant Bhatt, Dhruv Dhirendra Premani, Jay Chaudhari, Caiyong Wang, Jian Jiang, Chi Zhang, Qi Zhang, Iyyakutti Iyappan Ganapathi, Syed Sadaf Ali, Divya Velayudan, Maregu Assefa, Naoufel Werghi, Zachary A. Daniels, Le…

Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one co…

Bounding Distributional Shifts in World Modeling through Novelty Detection
Eric Jing, Abdeslam Boularias
https://arxiv.org/abs/2508.06096 https://arxiv.org…

Bounding Distributional Shifts in World Modeling through Novelty Detection
Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inference. To make a model-based planning algorithm more robust to the quality of the learned world model, we propose in this work to use a variational autoencoder as a novelty detector t…

Aligning Requirement for Large Language Model's Code Generation
Zhao Tian, Junjie Chen
https://arxiv.org/abs/2509.01313 https://arxiv.org/pdf/2509.0131…

Aligning Requirement for Large Language Model's Code Generation
Code generation refers to the automatic generation of source code based on a given programming specification, which has garnered significant attention particularly with the advancement of large language models (LLMs). However, due to the inherent complexity of real-world problems, the LLM-generated code often fails to fully align with the provided specification. While state-of-the-art agent-based techniques have been proposed to enhance LLM code generation, they overlook the critical issue of s…

Physics-Informed Neural Networks with Hard Nonlinear Equality and Inequality Constraints
Ashfaq Iftakher, Rahul Golder, M. M. Faruque Hasan
https://arxiv.org/abs/2507.08124 https://arxiv.org/pdf/2507.08124 https://arxiv.org/html/2507.08124
arXiv:2507.08124v1 Announce Type: new
Abstract: Traditional physics-informed neural networks (PINNs) do not guarantee strict constraint satisfaction. This is problematic in engineering systems where minor violations of governing laws can significantly degrade the reliability and consistency of model predictions. In this work, we develop KKT-Hardnet, a PINN architecture that enforces both linear and nonlinear equality and inequality constraints up to machine precision. It leverages a projection onto the feasible region through solving Karush-Kuhn-Tucker (KKT) conditions of a distance minimization problem. Furthermore, we reformulate the nonlinear KKT conditions using log-exponential transformation to construct a general sparse system with only linear and exponential terms, thereby making the projection differentiable. We apply KKT-Hardnet on both test problems and a real-world chemical process simulation. Compared to multilayer perceptrons and PINNs, KKT-Hardnet achieves higher accuracy and strict constraint satisfaction. This approach allows the integration of domain knowledge into machine learning towards reliable hybrid modeling of complex systems.
toXiv_bot_toot

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
Zikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong, Xiaorui Wang, Zhendong Mao
https://arxiv.org/abs/2509.09734

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian agentic AI. However, despite MCP's growing adoption, existing benchmarks often fail to capture real-world agent performance within this new paradigm, leading to a distorted perception of their true operational value and an inability to reliably differentiate p…

Google DeepMind releases its Genie 3 model, which can generate 3D worlds from a prompt and has enough visual memory for a few minutes of continuous interaction (Jay Peters/The Verge)
https://www.theverge.com/news/718723/google-ai-genie-3-model-video-g…

Google’s new AI model creates video game worlds in real time
Google DeepMind’s new Genie 3 AI world model is capable of generating real-time interactive 3D environments.

UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks
Peiran Wu, Yunze Liu, Zhengdong Zhu, Enmin Zhou, Shawn Shen
https://arxiv.org/abs/2507.11336

UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks
Real-world user-generated videos, especially on platforms like TikTok, often feature rich and intertwined audio visual content. However, existing video captioning benchmarks and models remain predominantly visual centric, overlooking the crucial role of audio in conveying scene dynamics, speaker intent, and narrative context. This lack of omni datasets and lightweight, capable models hampers progress in fine grained, multimodal video understanding. To address these challenges, we introduce UGC-…

Arbiter PUF: Uniqueness and Reliability Analysis Using Hybrid CMOS-Stanford Memristor Model
Tanvir Rahman, A. B. M. Harun-ur Rashid
https://arxiv.org/abs/2507.04461

Arbiter PUF: Uniqueness and Reliability Analysis Using Hybrid CMOS-Stanford Memristor Model
In an increasingly interconnected world, protecting electronic devices has grown more crucial because of the dangers of data extraction, reverse engineering, and hardware tampering. Producing chips in a third-party manufacturing company can let hackers change the design. As the Internet of Things (IoT) proliferates, physical attacks happen more, and conventional cryptography techniques do not function well. In this paper, we investigate the design and assessment of PUFs using the Stanford Memri…

An Approach to Grounding AI Model Evaluations in Human-derived Criteria
Sasha Mitts
https://arxiv.org/abs/2509.04676 https://arxiv.org/pdf/2509.04676

An Approach to Grounding AI Model Evaluations in Human-derived Criteria
In the rapidly evolving field of artificial intelligence (AI), traditional benchmarks can fall short in attempting to capture the nuanced capabilities of AI models. We focus on the case of physical world modeling and propose a novel approach to augment existing benchmarks with human-derived evaluation criteria, aiming to enhance the interpretability and applicability of model behaviors. Grounding our study in the Perception Test and OpenEQA benchmarks, we conducted in-depth interviews and large…

One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
Yuan Pu, Yazhe Niu, Jia Tang, Junyu Xiong, Shuai Hu, Hongsheng Li
https://arxiv.org/abs/2509.07945

One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
In heterogeneous multi-task learning, tasks not only exhibit diverse observation and action spaces but also vary substantially in intrinsic difficulty. While conventional multi-task world models like UniZero excel in single-task settings, we find that when handling large-scale heterogeneous environments, gradient conflicts and the loss of model plasticity often constrain their sample and computational efficiency. In this work, we address these challenges from two perspectives: the single learni…

Generalized User-Oriented Image Semantic Coding Empowered by Large Vision-Language Model
Sin-Yu Huang, Vincent W. S. Wong
https://arxiv.org/abs/2509.08913 https://

Generalized User-Oriented Image Semantic Coding Empowered by Large Vision-Language Model
Semantic communication has shown outstanding performance in preserving the overall source information in wireless transmission. For semantically rich content such as images, human users are often interested in specific regions depending on their intent. Moreover, recent semantic coding models are mostly trained on specific datasets. However, real-world applications may involve images out of the distribution of training dataset, which makes generalization a crucial but largely unexplored problem…

A profile of Robinhood CEO Vlad Tenev, whose personal fortune has surged 6x over the past year to $6.1B, as the company leans into tokenized stock derivatives (Nina Bambysheva/Forbes)
https://www.forbes.com/sites/ninabambyshev…

Inside Robinhood’s Crypto-Fueled Plan For World Domination
First Vlad Tenev blew up the brokerage industry’s fee model. Now, thanks in part to his full-on crypto embrace, he has increased his fortune sixfold to $6 billion as he embarks on a global financial services takeover with tokenized stocks, AI-powered investing and a bid to own the rails of the looming $124 trillion generational wealth transfer.

CoEx -- Co-evolving World-model and Exploration
Minsoo Kim, Seung-won Hwang
https://arxiv.org/abs/2507.22281 https://arxiv.org/pdf/2507.22281

CoEx -- Co-evolving World-model and Exploration
Planning in modern LLM agents relies on the utilization of LLM as an internal world model, acquired during pretraining. However, existing agent designs fail to effectively assimilate new observations into dynamic updates of the world model. This reliance on the LLM's static internal world model is progressively prone to misalignment with the underlying true state of the world, leading to the generation of divergent and erroneous plans. We introduce a hierarchical agent architecture, CoEx, in wh…

WorldVLA: Towards Autoregressive Action World Model
Jun Cen, Chaohui Yu, Hangjie Yuan, Yuming Jiang, Siteng Huang, Jiayan Guo, Xin Li, Yibing Song, Hao Luo, Fan Wang, Deli Zhao, Hao Chen
https://arxiv.org/abs/2506.21539

WorldVLA: Towards Autoregressive Action World Model
We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. The world model predicts future images by leveraging both action and image understanding, with the purpose of learning the underlying physics of the environment to improve action generation. Meanwhile, the action model generates the subsequent actions based on image observations,…

A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs
Andy Zhu, Yingjun Du
https://arxiv.org/abs/2509.09727 https://arxiv…

A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs
Question answering (QA) plays a central role in financial education, yet existing large language model (LLM) approaches often fail to capture the nuanced and specialized reasoning required for financial problem-solving. The financial domain demands multistep quantitative reasoning, familiarity with domain-specific terminology, and comprehension of real-world scenarios. We present a multi-agent framework that leverages role-based prompting to enhance performance on domain-specific QA. Our framew…

World Model Implanting for Test-time Adaptation of Embodied Agents
Minjong Yoo, Jinwoo Jang, Sihyung Yoon, Honguk Woo
https://arxiv.org/abs/2509.03956 https://

World Model Implanting for Test-time Adaptation of Embodied Agents
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining. To address this, we present a world model implanting framework (WorMI) that combines the reasoning capabilities of large language models (LLMs) with independently learned, domain-specific world models through test-time composition. By allowing seamless implantation and removal of the world models, the embodied agent's policy achieves and maintai…

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Heet Nitinkumar Dalsania
https://arxiv.org/abs/2507.07254 https://a…

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Modern deep learning implementations for medical imaging usually rely on large labeled datasets. These datasets are often difficult to obtain due to privacy concerns, high costs, and even scarcity of cases. In this paper, a label-efficient strategy is proposed for chest X-ray diagnosis that seeks to reflect real-world hospital scenarios. The experiments use the NIH Chest X-ray14 dataset and a pre-trained CLIP ViT-B/32 model. The model is adapted via partial fine-tuning of its visual encoder and…

Unveiling the Underwater World: CLIP Perception Model-Guided Underwater Image Enhancement
Jiangzhong Cao, Zekai Zeng, Xu Zhang, Huan Zhang, Chunling Fan, Gangyi Jiang, Weisi Lin
https://arxiv.org/abs/2507.06234

Unveiling the Underwater World: CLIP Perception Model-Guided Underwater Image Enhancement
High-quality underwater images are essential for both machine vision tasks and viewers with their aesthetic appeal.However, the quality of underwater images is severely affected by light absorption and scattering. Deep learning-based methods for Underwater Image Enhancement (UIE) have achieved good performance. However, these methods often overlook considering human perception and lack sufficient constraints within the solution space. Consequently, the enhanced images often suffer from diminish…

Reading Between the Lines: Classifying Resume Seniority with Large Language Models
Matan Cohen, Shira Shani, Eden Menahem, Yehudit Aperstein, Alexander Apartsin
https://arxiv.org/abs/2509.09229

Reading Between the Lines: Classifying Resume Seniority with Large Language Models
Accurately assessing candidate seniority from resumes is a critical yet challenging task, complicated by the prevalence of overstated experience and ambiguous self-presentation. In this study, we investigate the effectiveness of large language models (LLMs), including fine-tuned BERT architectures, for automating seniority classification in resumes. To rigorously evaluate model performance, we introduce a hybrid dataset comprising both real-world resumes and synthetically generated hard example…

A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
TRI LBM Team, Jose Barreiros, Andrew Beaulieu, Aditya Bhat, Rick Cory, Eric Cousineau, Hongkai Dai, Ching-Hsin Fang, Kunimatsu Hashimoto, Muhammad Zubair Irshad, Masha Itkina, Naveen Kuppuswamy, Kuan-Hui Lee, Katherine Liu, Dale McConachie, Ian McMahon, Haruki Nishimura, Calder Phillips-Grafflin, Charles Richter, Paarth Shah, Krishnan Srinivasan, Blake Wulfe, Chen Xu, Mengchao Zhang, Alex Alspach, Maya …

A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently, scaling data and model size has led to the development of capable language and vision foundation models, motivating large-scale efforts to create general-purpose robot foundation models. While these models have garnered significant enthusiasm and investment, meaningful evaluation of real-world performance remains a …

VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
C\'edric Bonhomme, Alexandre Dulaunoy
https://arxiv.org/abs/2507.03607 …

VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated into the Vulnerability-Lookup service.

LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
Yinglin Duan, Zhengxia Zou, Tongwei Gu, Wei Jia, Zhan Zhao, Luyi Xu, Xinzhu Liu, Hao Jiang, Kang Chen, Shuang Qiu
https://arxiv.org/abs/2509.05263

LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
Recent research has been increasingly focusing on developing 3D world models that simulate complex real-world scenarios. World models have found broad applications across various domains, including embodied AI, autonomous driving, entertainment, etc. A more realistic simulation with accurate physics will effectively narrow the sim-to-real gap and allow us to gather rich information about the real world conveniently. While traditional manual modeling has enabled the creation of virtual 3D scenes…

Activation Subspaces for Out-of-Distribution Detection
Bar{\i}\c{s} Z\"ong\"ur, Robin Hesse, Stefan Roth
https://arxiv.org/abs/2508.21695 https://

Activation Subspaces for Out-of-Distribution Detection
To ensure the reliability of deep models in real-world applications, out-of-distribution (OOD) detection methods aim to distinguish samples close to the training distribution (in-distribution, ID) from those farther away (OOD). In this work, we propose a novel OOD detection method that utilizes singular value decomposition of the weight matrix of the classification head to decompose the model's activations into decisive and insignificant components, which contribute maximally, respectively mini…

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
Kevin Saad, Vincenzo Petrone, Enrico Ferrentino, Pasquale Chiacchio, Francesco Braghin, Loris Roveda
https://arxiv.org/abs/2509.08440

Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks
As robotics gains popularity, interaction control becomes crucial for ensuring force tracking in manipulator-based tasks. Typically, traditional interaction controllers either require extensive tuning, or demand expert knowledge of the environment, which is often impractical in real-world applications. This work proposes a novel control strategy leveraging Neural Networks (NNs) to enhance the force-tracking behavior of a Direct Force Controller (DFC). Unlike similar previous approaches, it acco…

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
Katherine Liu, Sergey Zakharov, Dian Chen, Takuya Ikeda, Greg Shakhnarovich, Adrien Gaidon, Rares Ambrus
https://arxiv.org/abs/2508.03669

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World
We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first method of its kind to enable probabilistic pose and shape estimation. OmniShape is based on the key insight that shape completion can be decoupled into two multi-modal distributions: one capturing how measurements project into a normalized object reference frame defined by the dataset and the other modelling a prior …

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
Paul Scherer, Andreas Kirsch, Jake P. Taylor-King
https://arxiv.org/abs/2509.04363

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance tradeoff
Real-world experimental scenarios are characterized by the presence of heteroskedastic aleatoric uncertainty, and this uncertainty can be correlated in batched settings. The bias--variance tradeoff can be used to write the expected mean squared error between a model distribution and a ground-truth random variable as the sum of an epistemic uncertainty term, the bias squared, and an aleatoric uncertainty term. We leverage this relationship to propose novel active learning strategies that directl…

Hierarchical Reduced-Order Model Predictive Control for Robust Locomotion on Humanoid Robots
Adrian B. Ghansah, Sergio A. Esteban, Aaron D. Ames
https://arxiv.org/abs/2509.04722

Hierarchical Reduced-Order Model Predictive Control for Robust Locomotion on Humanoid Robots
As humanoid robots enter real-world environments, ensuring robust locomotion across diverse environments is crucial. This paper presents a computationally efficient hierarchical control framework for humanoid robot locomotion based on reduced-order models -- enabling versatile step planning and incorporating arm and torso dynamics to better stabilize the walking. At the high level, we use the step-to-step dynamics of the ALIP model to simultaneously optimize over step periods, step lengths, and…

Measuring Epistemic Humility in Multimodal Large Language Models
Bingkui Tong, Jiaer Xia, Sifeng Shang, Kaiyang Zhou
https://arxiv.org/abs/2509.09658 https://

Measuring Epistemic Humility in Multimodal Large Language Models
Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks an equally critical capability for trustworthy AI: recognizing when none of …

Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric Reasoning
Zhuang Chen, Guanqun Bi, Wen Zhang, Jiawei Hu, Aoyun Wang, Xiyao Xiao, Kun Feng, Minlie Huang
https://arxiv.org/abs/2508.04531

Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric Reasoning
Depression is a widespread mental disorder that affects millions worldwide. While automated depression assessment shows promise, most studies rely on limited or non-clinically validated data, and often prioritize complex model design over real-world effectiveness. In this paper, we aim to unveil the landscape of clinical depression assessment. We introduce C-MIND, a clinical neuropsychiatric multimodal diagnosis dataset collected over two years from real hospital visits. Each participant comple…

Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
Xiaodong Wang, Zijun He, Xin Yuan
https://arxiv.org/abs/2509.09352 https://

Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we propose a novel method for handling severe lighting and rich textures in intrinsic image decomposition, which enables to produce high-quality intrinsic images for real-world images.…

Back to the Features: DINO as a Foundation for Video World Models
Federico Baldassarre, Marc Szafraniec, Basile Terver, Vasil Khalidov, Francisco Massa, Yann LeCun, Patrick Labatut, Maximilian Seitzer, Piotr Bojanowski
https://arxiv.org/abs/2507.19468

Back to the Features: DINO as a Foundation for Video World Models
We present DINO-world, a powerful generalist video world model trained to predict future frames in the latent space of DINOv2. By leveraging a pre-trained image encoder and training a future predictor on a large-scale uncurated video dataset, DINO-world learns the temporal dynamics of diverse scenes, from driving and indoor scenes to simulated environments. We show that DINO-world outperforms previous models on a variety of video prediction benchmarks, e.g. segmentation and depth forecasting, a…

TriLiteNet: Lightweight Model for Multi-Task Visual Perception
Quang-Huy Che, Duc-Khai Lam
https://arxiv.org/abs/2509.04092 https://arxiv.org/pdf/2509.0409…

TriLiteNet: Lightweight Model for Multi-Task Visual Perception
Efficient perception models are essential for Advanced Driver Assistance Systems (ADAS), as these applications require rapid processing and response to ensure safety and effectiveness in real-world environments. To address the real-time execution needs of such perception models, this study introduces the TriLiteNet model. This model can simultaneously manage multiple tasks related to panoramic driving perception. TriLiteNet is designed to optimize performance while maintaining low computational…