Tootfinder

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki
https://arxiv.org/abs/2506.01952

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and demonstrate proficiency in general browsing tasks, a critical question emerges: Can they go beyond general browsing to robustly handle tasks that are tedious and complex, or chores that humans often avoid doing themselves? In this paper, we introduce WebChore…

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang, Zhijie Deng
https://arxiv.org/abs/2506.00411

LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (VLA) models and hierarchical architectures offer potential in embodied tasks, the former often falter in planning, and the latter can suffe…

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
Chenjun Xu, Bingbing Wen, Bin Han, Robert Wolfe, Lucy Lu Wang, Bill Howe
https://arxiv.org/abs/2506.00582

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We examine three LLMs, Llama-3-70B-instruct, Claude-3-Sonnet, and GPT-4o, on a range of QA tasks of varying difficulty, and show that models exhibit subtle differences from human patterns of overconfidence: less sensitive to task difficulty, and when prompted to answer based on different personas -- e.g., expert vs laym…

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov, O\u{g}uzhan Fatih Kar, Amir Zamir
https://arxiv.org/abs/2507.01955

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Multimodal foundation models, such as GPT-4o, have recently made remarkable progress, but it is not clear where exactly these models stand in terms of understanding vision. In this paper, we benchmark the performance of popular multimodal foundation models (GPT-4o, o4-mini, Gemini 1.5 Pro and Gemini 2.0 Flash, Claude 3.5 Sonnet, Qwen2-VL, Llama 3.2) on standard computer vision tasks (semantic segmentation, object detection, image classification, depth and surface normal prediction) using establ…

LLMs often nail short-term tasks but AI agents can spiral into insane meltdowns over time. This AI-powered vending machine tried to email the FBI to say it was a victim of cyberfraud and then declared its quantum state "collapsed":
https://www.linked…

Designing Visualization Widgets for Tangible Data Exploration: A Systematic Review
Haonan Yao, Lingyun Yu, Lijie Yao
https://arxiv.org/abs/2507.00775 https…

Designing Visualization Widgets for Tangible Data Exploration: A Systematic Review
We present a systematic review on tasks, interactions, and visualization widgets (refer to tangible entities that are used to accomplish data exploration tasks through specific interactions) in the context of tangible data exploration. Tangible widgets have been shown to reduce cognitive load, enable more natural interactions, and support the completion of complex data exploration tasks. Yet, the field lacks a structured understanding of how task types, interaction methods, and widget designs a…

Google calendar notifications are not cutting it... Anybody have suggestions on a better "organize all the stuff you have to / want to do" tool?
I'm not even quite sure what I want, other than "tasks that sat around for a year uncompleted should not auto-delete" and "tasks should be able to block other tasks".
I guess the "easy" option is a private github repo that is empty and only used as an issue tracker, but then I'd have to sig…

WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks
Zihao Sun, Meng Fang, Ling Chen
https://arxiv.org/abs/2507.00938 https://

WebArXiv: Evaluating Multimodal Agents on Time-Invariant arXiv Tasks
Recent progress in large language models (LLMs) has enabled the development of autonomous web agents capable of navigating and interacting with real websites. However, evaluating such agents remains challenging due to the instability and inconsistency of existing benchmarks, which often rely on dynamic content or oversimplified simulations. In this work, we introduce WebArXiv, a static and time-invariant benchmark comprising 275 web-based tasks grounded in the arXiv platform. WebArXiv ensures r…

A software developer explains how LLMs, especially AI agents, help automate tedious coding tasks and addresses concerns like hallucinations, job loss, and more (Thomas Ptacek/Fly)
https://fly.io/blog/youre-all-nuts/

My AI Skeptic Friends Are All Nuts
My smartest friends have bananas arguments about LLM coding.

Haptic Rapidly-Exploring Random Trees: A Sampling-based Planner for Quasi-static Manipulation Tasks
Lin Yang, Huu-Thiet Nguyen, Donghan Yu, Chen Lv, Domenico Campolo
https://arxiv.org/abs/2506.00351

Haptic Rapidly-Exploring Random Trees: A Sampling-based Planner for Quasi-static Manipulation Tasks
In this work, we explore how conventional motion planning algorithms can be reapplied to contact-rich manipulation tasks. Rather than focusing solely on efficiency, we investigate how manipulation aspects can be recast in terms of conventional motion-planning algorithms. Conventional motion planners, such as Rapidly-Exploring Random Trees (RRT), typically compute collision-free paths in configuration space. However, in manipulation tasks, intentional contact is often necessary. For example, whe…

Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks
Qiang Chen, Tianyang Han, Jin Li, Ye Luo, Yuxiao Wu, Xiaowei Zhang, Tuo Zhou
https://arxiv.org/abs/2506.00856

Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks
Can AI effectively perform complex econometric analysis traditionally requiring human expertise? This paper evaluates an agentic AI's capability to master econometrics, focusing on empirical analysis performance. We develop an ``Econometrics AI Agent'' built on the open-source MetaGPT framework. This agent exhibits outstanding performance in: (1) planning econometric tasks strategically, (2) generating and executing code, (3) employing error-based reflection for improved robustness, and (4) all…

This https://arxiv.org/abs/2503.19217 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages
The rapid evolution of large language models (LLMs) has opened new possibilities for automating various tasks in software development. This paper evaluates the capabilities of the Llama 2-70B model in automating these tasks for scientific applications written in commonly used programming languages. Using representative test problems, we assess the model's capacity to generate code, documentation, and unit tests, as well as its ability to translate existing code between commonly used programming…

This https://arxiv.org/abs/2505.06685 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMM_…

Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding
Emotion understanding in videos aims to accurately recognize and interpret individuals' emotional states by integrating contextual, visual, textual, and auditory cues. While Large Multimodal Models (LMMs) have demonstrated significant progress in general vision-language (VL) tasks, their performance in emotion-specific scenarios remains limited. Moreover, fine-tuning LMMs on emotion-related tasks often leads to catastrophic forgetting, hindering their ability to generalize across diverse tasks.…

Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based
Shuangquan Lyu, Yingnan Deng, Guiran Liu, Zhen Qi, Ruotong Wang
https://arxiv.org/abs/2507.00601

Transferable Modeling Strategies for Low-Resource LLM Tasks: A Prompt and Alignment-Based
This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient fine-tuning strategies. The method introduces knowledge alignment loss and soft prompt tuning to guide the model in effectively absorbing the structural features of target languages or tasks under minimal annotation. This enhances both generalization performance and tr…

" About half of all AI-generated code contains security flaws.
Veracode tasked over 100 different large language models with completing 80 separate coding tasks, from using different coding languages to building different types of applications. The results were not exactly inspiring if security is your top priority, with just 55% of tasks completed ultimately generating “secure” code."
Read This Before You Trust Any AI-Written Code
https://gizmodo.com/read-this-before-you-trust-any-ai-written-code-2000637243

This https://arxiv.org/abs/2405.20912 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

A Branch-Price-Cut-And-Switch Approach for Optimizing Team Formation and Routing for Airport Baggage Handling Tasks with Stochastic Travel Times
In airport operations, optimally using dedicated personnel for baggage handling tasks plays a crucial role in the design of resource-efficient processes. Teams of workers with different qualifications must be formed, and loading or unloading tasks must be assigned to them. Each task has a time window within which it can be started and should be finished. Violating these temporal restrictions incurs severe financial penalties for the operator. In practice, various components of this process are …

I am planning on moving my shit away from Notion.
The whole "2nd Brain" thing does not work for me (it just gives me busywork instead of doing something useful) so what I am looking for
- self-hostable
- should have a web interface I can use from any machine without installation
-I need "tasks", "projects" that contain tasks and "notes" (ideally optionally connected to projects and/or tasks)
- boards for tasks
- mobile …

SourceSplice: Source Selection for Machine Learning Tasks
Ambarish Singh, Romila Pradhan
https://arxiv.org/abs/2507.22186 https://arxiv.org/pdf/2507.22186

SourceSplice: Source Selection for Machine Learning Tasks
Data quality plays a pivotal role in the predictive performance of machine learning (ML) tasks - a challenge amplified by the deluge of data sources available in modern organizations.Prior work in data discovery largely focus on metadata matching, semantic similarity or identifying tables that should be joined to answer a particular query, but do not consider source quality for high performance of the downstream ML task.This paper addresses the problem of determining the best subset of data sou…

Reduced Efficiency in the Right Fronto-Parietal Attentional Network During Distractor Suppression in Mild Cognitive Impairment
Jatupong Oboun, Piyanon Charoenpoonpanich, Anna Raksapatcharawong, Chaipat Chunharas, Itthi Chatnuntawech, Chainarong Amornbunchornvej, Sirawaj Itthipuripat
https://arxiv.org/abs/2507.01433

Reduced Efficiency in the Right Fronto-Parietal Attentional Network During Distractor Suppression in Mild Cognitive Impairment
Mild Cognitive Impairment (MCI) is a critical transitional stage between normal cognitive aging and dementia, making its early detection essential. This study investigates the neural mechanisms of distractor suppression in MCI patients using EEG and behavioral data during an attention-cueing Eriksen flanker task. A cohort of 56 MCIs and 26 healthy controls (HCs) performed tasks with congruent and incongruent stimuli of varying saliency levels. During these tasks, EEG data were analyzed for alph…

This https://arxiv.org/abs/2406.13945 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
As large language models (LLMs) continue to advance and gain widespread use, establishing systematic and reliable evaluation methodologies for LLMs and vision-language models (VLMs) has become essential to ensure their real-world effectiveness and reliability. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban re…

Manus unveils Wide Research, an experimental feature that lets users on its Pro plan enlist dozens of parallelized AI agents for large-scale, high-volume tasks (Carl Franzen/VentureBeat)
https://venturebeat.com/ai/youv…

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks
Sarah Pungitore, Shashank Yadav, David Maughan, Vignesh Subbian
https://arxiv.org/abs/2507.23146

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks
Objective: Although computational phenotyping is a central informatics activity with resulting cohorts supporting a wide variety of applications, it is time-intensive because of manual data review. We previously assessed the ability of LLMs to perform computational phenotyping tasks using computable phenotypes for ARF respiratory support therapies. They successfully performed concept classification and classification of single-therapy phenotypes, but underperformed on multiple-therapy phenotype…

LLM Agents Should Employ Security Principles
Kaiyuan Zhang, Zian Su, Pin-Yu Chen, Elisa Bertino, Xiangyu Zhang, Ninghui Li
https://arxiv.org/abs/2505.24019

LLM Agents Should Employ Security Principles
Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to privacy leakage and system exploitation. This position paper argues that the well-established design principles in information security, which are commonly referred to as security principles, should be…

State Similarity in Modular Superconducting Quantum Processors with Classical Communications
Bujiao Wu, Changrong Xie, Peng Mi, Zhiyi Wu, Zechen Guo, Peisheng Huang, Wenhui Huang, Xuandong Sun, Jiawei Zhang, Libo Zhang, Jiawei Qiu, Xiayu Linpeng, Ziyu Tao, Ji Chu, Ji Jiang, Song Liu, Jingjing Niu, Yuxuan Zhou, Yuxuan Du, Wenhui Ren, Youpeng Zhong, Tongliang Liu, Dapeng Yu

State Similarity in Modular Superconducting Quantum Processors with Classical Communications
As quantum devices continue to scale, distributed quantum computing emerges as a promising strategy for executing large-scale tasks across modular quantum processors. A central challenge in this paradigm is verifying the correctness of computational outcomes when subcircuits are executed independently following circuit cutting. Here we propose a cross-platform fidelity estimation algorithm tailored for modular architectures. Our method achieves substantial reductions in sample complexity compar…

This https://arxiv.org/abs/2502.03503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Analyzing limits for in-context learning
We examine limits of in-context learning (ICL) in transformer models trained from scratch, focusing on function approximation tasks as a controlled setting to uncover fundamental behaviors. While we show empirically that transformer models can generalize, approximating unseen classes of polynomial (non linear) functions, they cannot generalize beyond certain values. We provide both empirical and mathematical arguments explaining that these limitations stem from architectural components, namely …

CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
Monoshi Kumar Roy, Simin Chen, Benjamin Steenhoek, Jinjun Peng, Gail Kaiser, Baishakhi Ray, Wei Le
https://arxiv.org/abs/2506.00750

CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or educational coding problems and focus on coarse-grained reasoning tasks such as input/output prediction, limiting their effectiveness in evaluating LLMs in practical SE contexts. To bridge this gap, we propose CodeSense, the first benchmark that makes available a …

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Aladin Djuhera, Swanand Ravindra Kadhe, Farhan Ahmed, Syed Zawad, Holger Boche, Walid Saad
https://arxiv.org/abs/2506.00062

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Fine-tuning large language models (LLMs) for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can degrade the safety alignment of LLMs, causing them to respond to harmful or unethical user queries. In this paper, we investigate this issue for telecom-tuned LLMs using three representative datasets fea…

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
Yang Li, Youssef Emad, Karthik Padthe, Jack Lanchantin, Weizhe Yuan, Thao Nguyen, Jason Weston, Shang-Wen Li, Dong Wang, Ilia Kulikov, Xian Li
https://arxiv.org/abs/2507.01921

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic study of what kind of reasoning demonstrations from the teacher are most effective in improving the student model's reasoning capabilities. In this work we curate high-quality "NaturalThoughts" by selecting reasoning traces from a strong teacher model based …

Deep Learning in Mild Cognitive Impairment Diagnosis using Eye Movements and Image Content in Visual Memory Tasks
Tom\'as Silva Santos Rocha, Anastasiia Mikhailova, Moreno I. Coco, Jos\'e Santos-Victor
https://arxiv.org/abs/2506.23016

Deep Learning in Mild Cognitive Impairment Diagnosis using Eye Movements and Image Content in Visual Memory Tasks
The global prevalence of dementia is projected to double by 2050, highlighting the urgent need for scalable diagnostic tools. This study utilizes digital cognitive tasks with eye-tracking data correlated with memory processes to distinguish between Healthy Controls (HC) and Mild Cognitive Impairment (MCI), a precursor to dementia. A deep learning model based on VTNet was trained using eye-tracking data from 44 participants (24 MCI, 20 HCs) who performed a visual memory task. The model utilizes …

Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings
Anirudh Nair, Adi Banerjee, Laurent Mombaerts, Matthew Hagen, Tarik Borogovac
https://arxiv.org/abs/2506.00178

Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings
Prompt engineering represents a critical bottleneck to harness the full potential of Large Language Models (LLMs) for solving complex tasks, as it requires specialized expertise, significant trial-and-error, and manual intervention. This challenge is particularly pronounced for tasks involving subjective quality assessment, where defining explicit optimization objectives becomes fundamentally problematic. Existing automated prompt optimization methods falter in these scenarios, as they typicall…

Source: GPT-5 improvements won't be comparable to the leaps in performance of earlier models, such as between GPT-3 in 2020 and GPT-4 in 2023 (The Information)
https://www.theinformation.com/articles/inside-openais-rocky-path-gpt-5

Inside OpenAI’s Rocky Path to GPT-5
OpenAI made waves across the industry in December when it published the results from its tests of artificial intelligence that performs better on tasks when it gets more time and computing power to process them. The results implied ChatGPT customers were about to be blown away by what the new AI ...

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Vira Joshi, Zifan Xu, Bo Liu, Peter Stone, Amy Zhang
https://arxiv.org/abs/2507.23172 ht…

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. At the same time, \emph{massively parallelized training} has gained popularity, not only for significantly accelerating data collection through GPU-accelerated simulation but also for enabling diverse data collection across multiple tasks by simulating heterogeneous scenes in p…

evMLP: An Efficient Event-Driven MLP Architecture for Vision
Zhentan Zheng
https://arxiv.org/abs/2507.01927 https://arxiv.org/pdf/250…

evMLP: An Efficient Event-Driven MLP Architecture for Vision
Deep neural networks have achieved remarkable results in computer vision tasks. In the early days, Convolutional Neural Networks (CNNs) were the mainstream architecture. In recent years, Vision Transformers (ViTs) have become increasingly popular. In addition, exploring applications of multi-layer perceptrons (MLPs) has provided new perspectives for research into vision model architectures. In this paper, we present evMLP accompanied by a simple event-driven local update mechanism. The proposed…

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Yifan Hao, Chenlu Ye, Chi Han, Tong Zhang
https://arxiv.org/abs/2506.01919

Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive theoretical understanding of this phenomenon remains limited. In this work, we investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability. Taking explorations on a typical sequence model, i.e, H…

IRanker: Towards Ranking Foundation Model
Tao Feng, Zhigang Hua, Zijie Lei, Yan Xie, Shuang Yang, Bo Long, Jiaxuan You
https://arxiv.org/abs/2506.21638 htt…

IRanker: Towards Ranking Foundation Model
Ranking tasks are ubiquitous, encompassing applications such as recommendation systems, LLM routing, and item re-ranking. We propose to unify these tasks using a single ranking foundation model (FM), as it eliminates the need for designing different models for each specific ranking task. However, unlike general supervision tasks in LLMs, ranking tasks do not have clear labels for supervision, posing great challenges to developing a ranking FM. To overcome these challenges, we propose IRanker, a…

This https://arxiv.org/abs/2411.16746 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

LoBAM: LoRA-Based Backdoor Attack on Model Merging
Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains. This scheme, in the meantime, may open up backdoor attack opportunities where one single malicious model can jeopardize the integrity of the merged model. Existing works try to demonstrate the risk of such attacks by assuming substantial computational resources, focusing on cases where the attacker can fully fine-tune the pre-trained m…

When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking Recovery
Shirong Xu, Jingnan Zhang, Junhui Wang
https://arxiv.org/abs/2507.01613

When Less Is More: Binary Feedback Can Outperform Ordinal Comparisons in Ranking Recovery
Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional wisdom. We propose a general parametric framework for modeling ordinal paired comparisons without ties. The model adopts a generalized additive structure, featuring a link function that quantifies the preference difference between two items and…

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Leander Melroy Maben, Gayathri Ganesh Lakshmy, Srijith Radhakrishnan, Siddhant Arora, Shinji Watanabe
https://arxiv.org/abs/2506.23049

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools …

Building Trustworthy Cognitive Monitoring for Safety-Critical Human Tasks: A Phased Methodological Approach
Maciej Grzeszczuk, Grzegorz Pochwatko, Barbara Karpowicz, Stanis{\l}aw Knapi\'nski, Wies{\l}aw Kope\'c
https://arxiv.org/abs/2506.22066

Building Trustworthy Cognitive Monitoring for Safety-Critical Human Tasks: A Phased Methodological Approach
Operators performing high-stakes, safety-critical tasks - such as air traffic controllers, surgeons, or mission control personnel - must maintain exceptional cognitive performance under variable and often stressful conditions. This paper presents a phased methodological approach to building cognitive monitoring systems for such environments. By integrating insights from human factors research, simulation-based training, sensor technologies, and fundamental psychological principles, the proposed…

This https://arxiv.org/abs/2402.02160 has been replaced.
link: https://scholar.google.com/scholar?q=a

Data Poisoning for In-context Learning
In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical issue of ICL's susceptibility to data poisoning attacks, an area not yet fully explored. We wonder whether ICL is vulnerable, with adversaries capable of manipulating example data to degrade model performance. To address this, we introduce ICLPoison, a speciali…

CODEMENV: Benchmarking Large Language Models on Code Migration
Keyuan Cheng, Xudong Shen, Yihao Yang, Tengyue Wang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang
https://arxiv.org/abs/2506.00894

CODEMENV: Benchmarking Large Language Models on Code Migration
Large language models (LLMs) have shown remarkable capabilities across various software engineering tasks; however, their effectiveness in code migration, adapting code to run in different environments, remains insufficiently studied. In this work, we introduce CODEMENV: Code Migration Across Environment, a new benchmark specifically designed to assess LLMs' abilities in code migration scenarios. CODEMENV consists of 922 examples spanning 19 Python and Java packages, and covers three core tasks…

An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
Davide Adamo, Marco Corneli, Manon Vuillien, Emmanuelle Vila
https://arxiv.org/abs/2507.00894

An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
Due to its invariance to rigid transformations such as rotations and reflections, Procrustes-Wasserstein (PW) was introduced in the literature as an optimal transport (OT) distance, alternative to Wasserstein and more suited to tasks such as the alignment and comparison of point clouds. Having that application in mind, we carefully build a space of discrete probability measures and show that over that space PW actually is a distance. Algorithms to solve the PW problems already exist, however we…

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, Kang Liu
https://arxiv.org/abs/2506.01710

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL)…

An interview with Claude AI product lead Scott White on Claude Code writing 90% of its own code, MCP, coding being accessible to non-technical workers, and more (Michael Nuñez/VentureBeat)
https://venturebeat.com/ai/from-chatbo

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Muhammad Qasim Ali, Aditya Sridhar, Shahbuland Matiana, Alex Wong, Mohammad Al-Sharman
https://arxiv.org/abs/2506.01182

Humanoid World Models: Open World Foundation Models for Humanoid Robotics
Humanoid robots have the potential to perform complex tasks in human centered environments but require robust predictive models to reason about the outcomes of their actions. We introduce Humanoid World Models (HWM) a family of lightweight open source video based models that forecast future egocentric observations conditioned on actions. We train two types of generative models Masked Transformers and FlowMatching on 100 hours of humanoid demonstrations. Additionally we explore architectural var…

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
Lei Yu, Yechao Zhang, Ziqi Zhou, Yang Wu, Wei Wan, Minghui Li, Shengshan Hu, Pei Xiaobing, Jing Wang
https://arxiv.org/abs/2505.23828

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced Retrieval-Augmented Generation (RAG) techniques, commonly used in Large Language Models (LLM), into VLM, incorporating external multi-modal knowledge to enhance the accuracy and practicality of VLM systems. Nev…

This https://arxiv.org/abs/2411.10877 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development
Despite the utility that Generative AI (GenAI) tools provide for tasks such as writing code, the use of these tools raises important legal questions and potential risks, particularly those associated with copyright law. As lawmakers and regulators engage with those questions, the views of users can provide relevant perspectives. In this paper, we provide: (1) a survey of 574 developers on the licensing and copyright aspects of GenAI for coding, as well as follow-up interviews; (2) a snapshot of…

Evaluation of LLMs for mathematical problem solving
Ruonan Wang, Runxi Wang, Yunwen Shen, Chengfeng Wu, Qinglin Zhou, Rohitash Chandra
https://arxiv.org/abs/2506.00309

Evaluation of LLMs for mathematical problem solving
Large Language Models (LLMs) have shown impressive performance on a range of educational tasks, but are still understudied for their potential to solve mathematical problems. In this study, we compare three prominent LLMs, including GPT-4o, DeepSeek-V3, and Gemini-2.0, on three mathematics datasets of varying complexities (GSM8K, MATH500, and UNSW datasets). We take a five-dimensional approach based on the Structured Chain-of-Thought (SCoT) framework to assess final answer correctness, step com…

ChatVis: Large Language Model Agent for Generating Scientific Visualizations
Tom Peterka, Tanwi Mallick, Orcun Yildiz, David Lenz, Cory Quammen, Berk Geveci
https://arxiv.org/abs/2507.23096

ChatVis: Large Language Model Agent for Generating Scientific Visualizations
Large language models (LLMs) are rapidly increasing in capability, but they still struggle with highly specialized programming tasks such as scientific visualization. We present an LLM assistant, ChatVis, that aids the LLM to generate Python code for ParaView scientific visualization tasks, without the need for retraining or fine-tuning the LLM. ChatVis employs chain-of-thought prompt simplification, retrieval-augmented prompt generation using a vector database of documentation and code example…

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Dongyi Ding, Tiannan Wang, Chenghao Zhu, Meiling Tao, Yuchen Eleanor Jiang, Wangchunshu Zhou
https://arxiv.org/abs/2507.01887

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Large language models (LLMs) excel at reasoning tasks requiring long thought sequences for planning, reflection, and refinement. However, their substantial model size and high computational demands are impractical for widespread deployment. Yet, small language models (SLMs) often struggle to learn long-form CoT reasoning due to their limited capacity, a phenomenon we refer to as the "SLMs Learnability Gap". To address this, we introduce \textbf{Mi}d-\textbf{Co}T \textbf{T}eacher \textbf{A}ssist…

PB&J: Peanut Butter and Joints for Damped Articulation
Avery S. Williamson, Michael J. Bennington, Ravesh Sukhnandan, Mrinali Nakhre, Yuemin Mao, Victoria A. Webster-Wood
https://arxiv.org/abs/2505.24860

PB&J: Peanut Butter and Joints for Damped Articulation
Many bioinspired robots mimic the rigid articulated joint structure of the human hand for grasping tasks, but experience high-frequency mechanical perturbations that can destabilize the system and negatively affect precision without a high-frequency controller. Despite having bandwidth-limited controllers that experience time delays between sensing and actuation, biological systems can respond successfully to and mitigate these high-frequency perturbations. Human joints include damping and stif…

Sources: GPT-5 shows improved performance in coding, particularly in practical software engineering tasks, outperforming prior OpenAI models and Claude Sonnet 4 (Stephanie Palazzolo/The Information)
https://www.theinformation.com/articles/openais-gpt-5-shines-coding…

OpenAI’s GPT-5 Shines in Coding Tasks
GPT-5 is almost here, and we’re hearing good things. The early reaction from at least one person who’s used the unreleased version was extremely positive.That’s good news for OpenAI. The ChatGPT creator has been under pressure to show major gains from its next big artificial intelligence model ...

This https://arxiv.org/abs/2410.02644 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLM-based agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, i…

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets
Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, Jiaxin Pei
https://arxiv.org/abs/2506.00073

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets
AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a future scenario where both consumers and merchants authorize AI agents to fully automate negotiations and transactions. We aim to answer two key questions: (1) Do different LLM agents vary in their ability to secure favorable deals for users? (2) What risks arise from fully automating deal-making with AI agents in consum…

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Tao Xiong, Xavier Hu, Wenyan Fan, Shengyu Zhang
https://arxiv.org/abs/2507.00606

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and efficiency. We introduce Mixture of Reasoning (MoR), a training framework that embeds diverse reasoning strategies into LLMs for autonomous, task-adaptive reasoning without external prompt engineering. MoR has two phases: Thought Generation, creating reasoning chain t…

Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration
Sophia DiCuffa, Amanda Zambrana, Priyanshi Yadav, Sashidhar Madiraju, Khushi Suman, Eman Abdullah AlOmar
https://arxiv.org/abs/2506.01604

Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration
The growing integration of AI tools in software development, particularly Large Language Models (LLMs) such as ChatGPT, has revolutionized how developers approach coding tasks. However, achieving high-quality code often requires iterative interactions, which can be time-consuming and inefficient. This paper explores the application of structured prompt patterns to minimize the number of interactions required for satisfactory AI-assisted code generation. Using the DevGPT dataset, we analyzed sev…

Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
Alice Qian Zhang, Ryland Shaw, Laura Dabbish, Jina Suh, Hong Shen
https://arxiv.org/abs/2505.24246

Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowd workers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to wor…

This https://arxiv.org/abs/2503.22030 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Bayesian Inferential Motion Planning Using Heavy-Tailed Distributions
Robots rely on motion planning to navigate safely and efficiently while performing various tasks. In this paper, we investigate motion planning through Bayesian inference, where motion plans are inferred based on planning objectives and constraints. However, existing Bayesian motion planning methods often struggle to explore low-probability regions of the planning space, where high-quality plans may reside. To address this limitation, we propose the use of heavy-tailed distributions -- specific…

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
Yifan Hao, Xingyuan Pan, Hanning Zhang, Chenlu Ye, Rui Pan, Tong Zhang
https://arxiv.org/abs/2506.01901

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision models, ensembling a pretrained model with its fine-tuned counterpart has been shown to mitigate this issue. In this work, we demonstrate that the same holds for language models, and, more strikingly, we observe an overadaptation phenomenon: the ensemble mod…

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Jiandong Shao, Yao Lu, Jianfei Yang
https://arxiv.org/abs/2506.01734 https://

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Large Language Models (LLMs) exhibit impressive performance on complex reasoning tasks, yet they frequently fail on basic numerical problems, producing incorrect outputs. Inspired by Benford's Law -- a statistical pattern where lower digits occur more frequently as leading digits -- we hypothesize that the long-tailed digit distributions in web-collected corpora may be learned by LLMs during pretraining, leading to biased numerical generation. To investigate the hypothesis, we first examine whe…

Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems
Ronny Ko, Jiseong Jeong, Shuyuan Zheng, Chuan Xiao, Taewan Kim, Makoto Onizuka, Wonyong Shin
https://arxiv.org/abs/2505.23847

Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems
Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership. Yet, cross-domain collaboration shatters the unified trust assumptions behind current alignment and containment techniques. An agent benign in isolation may, when receiving messages from an untrusted peer, leak secrets or viola…

Human-Machine Collaboration-Guided Space Design: Combination of Machine Learning Models and Humanistic Design Concepts
Yuxuan Yang
https://arxiv.org/abs/2507.01776

Human-Machine Collaboration-Guided Space Design: Combination of Machine Learning Models and Humanistic Design Concepts
The integration of machine learning (ML) into spatial design holds immense potential for optimizing space utilization, enhancing functionality, and streamlining design processes. ML can automate tasks, predict performance outcomes, and tailor spaces to user preferences. However, the emotional, cultural, and aesthetic dimensions of design remain crucial for creating spaces that truly resonate with users-elements that ML alone cannot address. The key challenge lies in harmonizing data-driven effi…

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Guobin Zhu, Rui Zhou, Wenkang Ji, Shiyu Zhao
https://arxiv.org/abs/2506.01538

LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in single-robot settings, but their application in multi-robot systems remains largely unexplored. This paper introduces a novel LLM-Aided MARL (LAMARL) approach, which integrates MARL with LLMs, significantly enhancing sample efficiency without requiring manual design. LA…

iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
Shuai Wang, Yinan Yu
https://arxiv.org/abs/2506.01784 https://

iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
While Large Language Models (LLMs) excel at many natural language processing tasks, they often suffer from factual inaccuracies in knowledge-intensive scenarios. Integrating external knowledge resources, particularly knowledge graphs (KGs), provides a transparent and updatable foundation for more reliable reasoning. Knowledge Base Question Answering (KBQA), which queries and reasons over KGs, is central to this effort, especially for complex, multi-hop queries. However, multi-hop reasoning pose…

Fodor and Pylyshyn's Legacy - Still No Human-like Systematic Compositionality in Neural Networks
Tim Woydt, Moritz Willig, Antonia W\"ust, Lukas Helff, Wolfgang Stammer, Constantin A. Rothkopf, Kristian Kersting
https://arxiv.org/abs/2506.01820

Fodor and Pylyshyn's Legacy - Still No Human-like Systematic Compositionality in Neural Networks
Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in presenting models for robust adaptation to novel environments, it is important to refrain from making unsupported claims about the performance of meta-learning systems that ultimately do not stand up to scrutiny. While Fodor and Pylyshyn famously posited that neural networks inherently lack this capacity as they are unab…

This https://arxiv.org/abs/2502.11844 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

BaxBench: Can LLMs Generate Correct and Secure Backends?
Automatic program generation has long been a fundamental challenge in computer science. Recent benchmarks have shown that large language models (LLMs) can effectively generate code at the function level, make code edits, and solve algorithmic coding tasks. However, to achieve full automation, LLMs should be able to generate production-quality, self-contained application modules. To evaluate the capabilities of LLMs in solving this challenge, we introduce BaxBench, a novel evaluation benchmark c…

Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts
Anjali Singh, Zhitong Guan, Soo Young Rieh
https://arxiv.org/abs/2505.24014 …

Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts
The growing use of Generative AI (GenAI) conversational search tools has raised concerns about their effects on people's metacognitive engagement, critical thinking, and learning. As people increasingly rely on GenAI to perform tasks such as analyzing and applying information, they may become less actively engaged in thinking and learning. This study examines whether metacognitive prompts - designed to encourage people to pause, reflect, assess their understanding, and consider multiple perspec…

This https://arxiv.org/abs/2306.07569 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Ontological Component-based Description of Robot Capabilities
A key aspect of a robot's knowledge base is self-awareness about what it is capable of doing. It allows to define which tasks it can be assigned to and which it cannot. We will refer to this knowledge as the Capability concept. As capabilities stems from the components the robot owns, they can be linked together. In this work, we hypothesize that this concept can be inferred from the components rather than merely linked to them. Therefore, we introduce an ontological means of inferring the agen…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
Jingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao
https://arxiv.org/abs/2506.00618 https://…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
Zhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang, Dongfei Cui, Qinjian Zhao, Hui Shen, Jing Xiong, Yi Xin, Yifan Jiang, Yangfan He, Mi Zhang, Shen Yan
https://arxiv.org/abs/2506.01713

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges…

Email as the Interface to Generative AI Models: Seamless Administrative Automation
Andres Navarro, Carlos de Quinto, Jos\'e Alberto Hern\'andez
https://arxiv.org/abs/2506.23850

Email as the Interface to Generative AI Models: Seamless Administrative Automation
This paper introduces a novel architectural framework that integrates Large Language Models (LLMs) with email interfaces to automate administrative tasks, specifically targeting accessibility barriers in enterprise environments. The system connects email communication channels with Optical Character Recognition (OCR) and intelligent automation, enabling non-technical administrative staff to delegate complex form-filling and document processing tasks using familiar email interfaces. By treating …

On the Surprising Efficacy of LLMs for Penetration-Testing
Andreas Happe, J\"urgen Cito
https://arxiv.org/abs/2507.00829 https://

On the Surprising Efficacy of LLMs for Penetration-Testing
This paper presents a critical examination of the surprising efficacy of Large Language Models (LLMs) in penetration testing. The paper thoroughly reviews the evolution of LLMs and their rapidly expanding capabilities which render them increasingly suitable for complex penetration testing operations. It systematically details the historical adoption of LLMs in both academic research and industry, showcasing their application across various offensive security tasks and covering broader phases of…

Black-box Adversarial Attacks on CNN-based SLAM Algorithms
Maria Rafaela Gkeka, Bowen Sun, Evgenia Smirni, Christos D. Antonopoulos, Spyros Lalis, Nikolaos Bellas
https://arxiv.org/abs/2505.24654

Black-box Adversarial Attacks on CNN-based SLAM Algorithms
Continuous advancements in deep learning have led to significant progress in feature detection, resulting in enhanced accuracy in tasks like Simultaneous Localization and Mapping (SLAM). Nevertheless, the vulnerability of deep neural networks to adversarial attacks remains a challenge for their reliable deployment in applications, such as navigation of autonomous agents. Even though CNN-based SLAM algorithms are a growing area of research there is a notable absence of a comprehensive presentati…

This https://arxiv.org/abs/2407.15325 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Odyssey: Empowering Minecraft Agents with Open-World Skills
Recent studies have delved into constructing generalist agents for open-world environments like Minecraft. Despite the encouraging results, existing efforts mainly focus on solving basic programmatic tasks, e.g., material collection and tool-crafting following the Minecraft tech-tree, treating the ObtainDiamond task as the ultimate goal. This limitation stems from the narrowly defined set of actions available to agents, requiring them to learn effective long-horizon strategies from scratch. Con…

Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor
Moahmmadamin Shafiei, Hamidreza Saffari
https://arxiv.org/abs/2506.01819

Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor
With the recent advances in Artificial Intelligence (AI) and Large Language Models (LLMs), the automation of daily tasks, like automatic writing, is getting more and more attention. Hence, efforts have focused on aligning LLMs with human values, yet humor, particularly professional industrial humor used in workplaces, has been largely neglected. To address this, we develop a dataset of professional humor statements along with features that determine the appropriateness of each statement. Our ev…

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
Sixiang Chen, Jiaming Liu, Siyuan Qian, Han Jiang, Lily Li, Renrui Zhang, Zhuoyang Liu, Chenyang Gu, Chengkai Hou, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
https://arxiv.org/abs/2507.01961

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
Recently, mobile manipulation has attracted increasing attention for enabling language-conditioned robotic control in household tasks. However, existing methods still face challenges in coordinating mobile base and manipulator, primarily due to two limitations. On the one hand, they fail to explicitly model the influence of the mobile base on manipulator control, which easily leads to error accumulation under high degrees of freedom. On the other hand, they treat the entire mobile manipulation …

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Jennifer Chen, Aidar Myrzakhan, Yaxin Luo, Hassaan Muhammad Khan, Sondos Mahmoud Bsharat, Zhiqiang Shen
https://arxiv.org/abs/2506.01954

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
Retrieval-Augmented Generation (RAG) methods have proven highly effective for tasks requiring factual consistency and robust knowledge retrieval. However, large-scale RAG systems consume significant computational resources and are prone to generating hallucinated content from Humans. In this work, we introduce $\texttt{DRAG}$, a novel framework for distilling RAG knowledge from large-scale Language Models (LLMs) into small LMs (SLMs). Our approach leverages evidence- and knowledge graph-based d…

This https://arxiv.org/abs/2406.13948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

CityGPT: Empowering Urban Spatial Cognition of Large Language Models
Large language models(LLMs), with their powerful language generation and reasoning capabilities, have already achieved notable success in many domains, e.g., math and code generation. However, they often fall short when tackling real-life geospatial tasks within urban environments. This limitation stems from a lack of physical world knowledge and relevant data during training. To address this gap, we propose \textit{CityGPT}, a systematic framework designed to enhance LLMs' understanding of urb…

Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
Shivansh Patel, Shraddhaa Mohan, Hanlin Mai, Unnat Jain, Svetlana Lazebnik, Yunzhu Li
https://arxiv.org/abs/2507.00990

Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as pouring, wiping, and mixing--purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. Given a language command and an initial scene image, a video diffusion model generates potential demonstration videos, and a vision-language model (VLM) automatically filters out results that do not follow the comm…

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao
https://arxiv.org/abs/2507.00322

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of these errors across LMs of varying sizes (124M-7B) to both understand and mitigate the errors. Our study reveals that LMs rely on a number of components (attention heads and FF neurons) that independently make their own predictions. While some components reli…

DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
Yongkang Xiao, Sinian Zhang, Yi Dai, Huixue Zhou, Jue Hou, Jie Ding, Rui Zhang
https://arxiv.org/abs/2506.00708

DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
Knowledge graph completion (KGC) aims to predict missing triples in knowledge graphs (KGs) by leveraging existing triples and textual information. Recently, generative large language models (LLMs) have been increasingly employed for graph tasks. However, current approaches typically encode graph context in textual form, which fails to fully exploit the potential of LLMs for perceiving and reasoning about graph structures. To address this limitation, we propose DrKGC (Dynamic Subgraph Retrieval-…

DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation
Martin Peticco, Gabriella Ulloa, John Marangola, Pulkit Agrawal
https://arxiv.org/abs/2507.01008

DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation
We present the DexWrist, a compliant robotic wrist designed to advance robotic manipulation in highly-constrained environments, enable dynamic tasks, and speed up data collection. DexWrist is designed to be close to the functional capabilities of the human wrist and achieves mechanical compliance and a greater workspace as compared to existing robotic wrist designs. The DexWrist can supercharge policy learning by (i) enabling faster teleoperation and therefore making data collection more scalab…

Question Decomposition for Retrieval-Augmented Generation
Paul J. L. Ammann, Jonas Golde, Alan Akbik
https://arxiv.org/abs/2507.00355 https://

Question Decomposition for Retrieval-Augmented Generation
Grounding large language models (LLMs) in verifiable external sources is a well-established strategy for generating reliable answers. Retrieval-augmented generation (RAG) is one such approach, particularly effective for tasks like question answering: it retrieves passages that are semantically related to the question and then conditions the model on this evidence. However, multi-hop questions, such as "Which company among NVIDIA, Apple, and Google made the biggest profit in 2023?," challenge RA…

What do professional software developers need to know to succeed in an age of Artificial Intelligence?
Matthew Kam, Cody Miller, Miaoxin Wang, Abey Tidwell, Irene A. Lee, Joyce Malyn-Smith, Beatriz Perez, Vikram Tiwari, Joshua Kenitzer, Andrew Macvean, Erin Barrar
https://arxiv.org/abs/2506.00202…

What do professional software developers need to know to succeed in an age of Artificial Intelligence?
Generative AI is showing early evidence of productivity gains for software developers, but concerns persist regarding workforce disruption and deskilling. We describe our research with 21 developers at the cutting edge of using AI, summarizing 12 of their work goals we uncovered, together with 75 associated tasks and the skills & knowledge for each, illustrating how developers use AI at work. From all of these, we distilled our findings in the form of 5 insights. We found that the skills & know…

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
Aditya Tomar, Rudra Murthy, Pushpak Bhattacharyya
https://arxiv.org/abs/2507.01715

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
Bias and stereotypes in language models can cause harm, especially in sensitive areas like content moderation and decision-making. This paper addresses bias and stereotype detection by exploring how jointly learning these tasks enhances model performance. We introduce StereoBias, a unique dataset labeled for bias and stereotype detection across five categories: religion, gender, socio-economic status, race, profession, and others, enabling a deeper study of their relationship. Our experiments c…

Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons
Chi Chiu So, Yueyue Sun, Jun-Min Wang, Siu Pang Yung, Anthony Wai Keung Loh, Chun Pong Chau
https://arxiv.org/abs/2506.23128

Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons
How far are Large Language Models (LLMs) in performing deep relational reasoning? In this paper, we evaluate and compare the reasoning capabilities of three cutting-edge LLMs, namely, DeepSeek-R1, DeepSeek-V3 and GPT-4o, through a suite of carefully designed benchmark tasks in family tree and general graph reasoning. Our experiments reveal that DeepSeek-R1 consistently achieves the highest F1-scores across multiple tasks and problem sizes, demonstrating strong aptitude in logical deduction and …

DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
Zhao Mandi, Yifan Hou, Dieter Fox, Yashraj Narang, Ajay Mandlekar, Shuran Song
https://arxiv.org/abs/2505.24853

DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which is challenging due to large action space, spatiotemporal discontinuities, and embodiment gap between human and robot hands. We propose DexMachina, a novel curriculum-based algorithm: the key idea is to use virtual object controllers with decaying strength: an object is first…

NAVER LABS Europe Submission to the Instruction-following Track
Beomseok Lee, Marcely Zanon Boito, Laurent Besacier, Ioan Calapodescu
https://arxiv.org/abs/2506.01808

NAVER LABS Europe Submission to the Instruction-following Track
In this paper we describe NAVER LABS Europe submission to the instruction-following speech processing short track at IWSLT 2025. We participate in the constrained settings, developing systems that can simultaneously perform ASR, ST, and SQA tasks from English speech input into the following target languages: Chinese, Italian, and German. Our solution leverages two pretrained modules: (1) a speech-to-LLM embedding projector trained using representations from the SeamlessM4T-v2-large speech encod…

Pok\'eAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
Zihao Liu, Xinhang Sui, Yueran Song, Siwen Wang
https://arxiv.org/abs/2506.23689

PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon Red. Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set. The Planning Agent functions as the central brain, generating tasks to progress through the game. These tasks are then delegated to the Execution Agent, which carries them out within the game environment. Up…

This https://arxiv.org/abs/2410.00425 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. ManiSkill3 supports GPU parallelization of many aspects including simulation+re…

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu
https://arxiv.org/abs/2506.00320

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we propose Dyna-Think, a thinking framework that integrates planning with an internal world model with re…

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
Zhi Jing, Siyuan Yang, Jicong Ao, Ting Xiao, Yugang Jiang, Chenjia Bai
https://arxiv.org/abs/2507.00833

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning
For robotic manipulation, existing robotics datasets and simulation benchmarks predominantly cater to robot-arm platforms. However, for humanoid robots equipped with dual arms and dexterous hands, simulation tasks and high-quality demonstrations are notably lacking. Bimanual dexterous manipulation is inherently more complex, as it requires coordinated arm movements and hand operations, making autonomous data collection challenging. This paper presents HumanoidGen, an automated task creation and…

Control-R: Towards controllable test-time scaling
Di Zhang, Weida Wang, Junxian Li, Xunzhi Wang, Jiatong Li, Jianbo Wu, Jingdi Lei, Haonan He, Peng Ye, Shufei Zhang, Wanli Ouyang, Yuqiang Li, Dongzhan Zhou
https://arxiv.org/abs/2506.00189

Control-R: Towards controllable test-time scaling
This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning Control Fields (RCF)--a novel test-time approach that injects structured control signals to guide reasoning from a tree search perspective. RCF enables models to adjust reasoning effort according to given control conditions when solving complex tasks. Additionally, we present the Control-R-4K dataset, which consists …

This https://arxiv.org/abs/2505.12583 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
Recent Foundation Model-enabled robotics (FMRs) display greatly improved general-purpose skills, enabling more adaptable automation than conventional robotics. Their ability to handle diverse tasks thus creates new opportunities to replace human labor. However, unlike general foundation models, FMRs interact with the physical world, where their actions directly affect the safety of humans and surrounding objects, requiring careful deployment and control. Based on this proposition, our survey co…

This https://arxiv.org/abs/2502.20817 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning-Based Leader Localization for Underwater Vehicles With Optical-Acoustic-Pressure Sensor Fusion
Underwater vehicles have emerged as a critical technology for exploring and monitoring aquatic environments. The deployment of multi-vehicle systems has gained substantial interest due to their capability to perform collaborative tasks with improved efficiency. However, achieving precise localization of a leader underwater vehicle within a multi-vehicle configuration remains a significant challenge, particularly in dynamic and complex underwater conditions. To address this issue, this paper pre…

HoMeR: Learning In-the-Wild Mobile Manipulation via Hybrid Imitation and Whole-Body Control
Priya Sundaresan, Rhea Malhotra, Phillip Miao, Jingyun Yang, Jimmy Wu, Hengyuan Hu, Rika Antonova, Francis Engelmann, Dorsa Sadigh, Jeannette Bohg
https://arxiv.org/abs/2506.01185

HoMeR: Learning In-the-Wild Mobile Manipulation via Hybrid Imitation and Whole-Body Control
We introduce HoMeR, an imitation learning framework for mobile manipulation that combines whole-body control with hybrid action modes that handle both long-range and fine-grained motion, enabling effective performance on realistic in-the-wild tasks. At its core is a fast, kinematics-based whole-body controller that maps desired end-effector poses to coordinated motion across the mobile base and arm. Within this reduced end-effector action space, HoMeR learns to switch between absolute pose pred…

This https://arxiv.org/abs/2505.21906 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
Vision-language-action (VLA) models have emerged as the next generation of models in robotics. However, despite leveraging powerful pre-trained Vision-Language Models (VLMs), existing end-to-end VLA systems often lose key capabilities during fine-tuning as the model adapts to specific robotic tasks. We argue that a generalizable VLA model should retain and expand upon the VLM's core competencies: 1) Open-world embodied reasoning - the VLA should inherit the knowledge from VLM, i.e., recognize a…

Parallel Transmission Aware Co-Design: Enhancing Manipulator Performance Through Actuation-Space Optimization
Rohit Kumar, Melya Boukheddimi, Dennis Mronga, Shivesh Kumar, Frank Kirchner
https://arxiv.org/abs/2507.00644

Parallel Transmission Aware Co-Design: Enhancing Manipulator Performance Through Actuation-Space Optimization
In robotics, structural design and behavior optimization have long been considered separate processes, resulting in the development of systems with limited capabilities. Recently, co-design methods have gained popularity, where bi-level formulations are used to simultaneously optimize the robot design and behavior for specific tasks. However, most implementations assume a serial or tree-type model of the robot, overlooking the fact that many robot platforms incorporate parallel mechanisms. In t…

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis
https://arxiv.org/abs/2506.01196

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural language instructions and multi-view RGBD observations to quasi-static robot actions. 3D-aware robot policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects. On …

RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
Yi Ru Wang, Carter Ung, Grant Tannert, Jiafei Duan, Josephine Li, Amy Le, Rishabh Oswal, Markus Grotz, Wilbert Pumacay, Yuquan Deng, Ranjay Krishna, Dieter Fox, Siddhartha Srinivasa
https://arxiv.org/abs/2507.00435…

RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
We present RoboEval, a simulation benchmark and structured evaluation framework designed to reveal the limitations of current bimanual manipulation policies. While prior benchmarks report only binary task success, we show that such metrics often conceal critical weaknesses in policy behavior -- such as poor coordination, slipping during grasping, or asymmetric arm usage. RoboEval introduces a suite of tiered, semantically grounded tasks decomposed into skill-specific stages, with variations tha…