Tootfinder

House passes Big Beautiful Bill Act, sending it to Trump after bruising struggle (New York Post)
https://nypost.com/2025/07/03/us-news/house-passes-big-beautiful-bill-act-sending-it-to-trump-after-bruising-struggle/
http://www.memeorandum.com/250703/p100#a250703p100

"People in Romania's southwest struggle to access water as one third of country faces drought"
#Romania #Drought

Drought strikes one third of Romania as residents struggle for water
Romania's southwestern Dolj county struggles with severe drought. Villagers in Teascu din Deal trek long distances for water, facing harsh conditions daily.

Please help Aseel and her family eat this week if you can.
(I have spoken with and am in touch with Aseel over Signal and I can vouch that the account and campaign are real and your donations go to a family in need in Gaza.)
#gaza #aid

Third earthquake hits Afghanistan as death toll rises above 2,200
South-east of country rocked as rescuers struggle to find survivors of first quake
https://www.theguardian.com/world/2025/sep/04/third-earthquake-…

Should we teach vibe coding? Here's why not.
Should AI coding be taught in undergrad CS education?
1/2
I teach undergraduate computer science labs, including for intro and more-advanced core courses. I don't publish (non-negligible) scholarly work in the area, but I've got years of craft expertise in course design, and I do follow the academic literature to some degree. In other words, In not the world's leading expert, but I have spent a lot of time thinking about course design, and consider myself competent at it, with plenty of direct experience in what knowledge & skills I can expect from students as they move through the curriculum.
I'm also strongly against most uses of what's called "AI" these days (specifically, generative deep neutral networks as supplied by our current cadre of techbro). There are a surprising number of completely orthogonal reasons to oppose the use of these systems, and a very limited number of reasonable exceptions (overcoming accessibility barriers is an example). On the grounds of environmental and digital-commons-pollution costs alone, using specifically the largest/newest models is unethical in most cases.
But as any good teacher should, I constantly question these evaluations, because I worry about the impact on my students should I eschew teaching relevant tech for bad reasons (and even for his reasons). I also want to make my reasoning clear to students, who should absolutely question me on this. That inspired me to ask a simple question: ignoring for one moment the ethical objections (which we shouldn't, of course; they're very stark), at what level in the CS major could I expect to teach a course about programming with AI assistance, and expect students to succeed at a more technically demanding final project than a course at the same level where students were banned from using AI? In other words, at what level would I expect students to actually benefit from AI coding "assistance?"
To be clear, I'm assuming that students aren't using AI in other aspects of coursework: the topic of using AI to "help you study" is a separate one (TL;DR it's gross value is not negative, but it's mostly not worth the harm to your metacognitive abilities, which AI-induced changes to the digital commons are making more important than ever).
So what's my answer to this question?
If I'm being incredibly optimistic, senior year. Slightly less optimistic, second year of a masters program. Realistic? Maybe never.
The interesting bit for you-the-reader is: why is this my answer? (Especially given that students would probably self-report significant gains at lower levels.) To start with, [this paper where experienced developers thought that AI assistance sped up their work on real tasks when in fact it slowed it down] (https://arxiv.org/abs/2507.09089) is informative. There are a lot of differences in task between experienced devs solving real bugs and students working on a class project, but it's important to understand that we shouldn't have a baseline expectation that AI coding "assistants" will speed things up in the best of circumstances, and we shouldn't trust self-reports of productivity (or the AI hype machine in general).
Now we might imagine that coding assistants will be better at helping with a student project than at helping with fixing bugs in open-source software, since it's a much easier task. For many programming assignments that have a fixed answer, we know that many AI assistants can just spit out a solution based on prompting them with the problem description (there's another elephant in the room here to do with learning outcomes regardless of project success, but we'll ignore this over too, my focus here is on project complexity reach, not learning outcomes). My question is about more open-ended projects, not assignments with an expected answer. Here's a second study (by one of my colleagues) about novices using AI assistance for programming tasks. It showcases how difficult it is to use AI tools well, and some of these stumbling blocks that novices in particular face.
But what about intermediate students? Might there be some level where the AI is helpful because the task is still relatively simple and the students are good enough to handle it? The problem with this is that as task complexity increases, so does the likelihood of the AI generating (or copying) code that uses more complex constructs which a student doesn't understand. Let's say I have second year students writing interactive websites with JavaScript. Without a lot of care that those students don't know how to deploy, the AI is likely to suggest code that depends on several different frameworks, from React to JQuery, without actually setting up or including those frameworks, and of course three students would be way out of their depth trying to do that. This is a general problem: each programming class carefully limits the specific code frameworks and constructs it expects students to know based on the material it covers. There is no feasible way to limit an AI assistant to a fixed set of constructs or frameworks, using current designs. There are alternate designs where this would be possible (like AI search through adaptation from a controlled library of snippets) but those would be entirely different tools.
So what happens on a sizeable class project where the AI has dropped in buggy code, especially if it uses code constructs the students don't understand? Best case, they understand that they don't understand and re-prompt, or ask for help from an instructor or TA quickly who helps them get rid of the stuff they don't understand and re-prompt or manually add stuff they do. Average case: they waste several hours and/or sweep the bugs partly under the rug, resulting in a project with significant defects. Students in their second and even third years of a CS major still have a lot to learn about debugging, and usually have significant gaps in their knowledge of even their most comfortable programming language. I do think regardless of AI we as teachers need to get better at teaching debugging skills, but the knowledge gaps are inevitable because there's just too much to know. In Python, for example, the LLM is going to spit out yields, async functions, try/finally, maybe even something like a while/else, or with recent training data, the walrus operator. I can't expect even a fraction of 3rd year students who have worked with Python since their first year to know about all these things, and based on how students approach projects where they have studied all the relevant constructs but have forgotten some, I'm not optimistic seeing these things will magically become learning opportunities. Student projects are better off working with a limited subset of full programming languages that the students have actually learned, and using AI coding assistants as currently designed makes this impossible. Beyond that, even when the "assistant" just introduces bugs using syntax the students understand, even through their 4th year many students struggle to understand the operation of moderately complex code they've written themselves, let alone written by someone else. Having access to an AI that will confidently offer incorrect explanations for bugs will make this worse.
To be sure a small minority of students will be able to overcome these problems, but that minority is the group that has a good grasp of the fundamentals and has broadened their knowledge through self-study, which earlier AI-reliant classes would make less likely to happen. In any case, I care about the average student, since we already have plenty of stuff about our institutions that makes life easier for a favored few while being worse for the average student (note that our construction of that favored few as the "good" students is a large part of this problem).
To summarize: because AI assistants introduce excess code complexity and difficult-to-debug bugs, they'll slow down rather than speed up project progress for the average student on moderately complex projects. On a fixed deadline, they'll result in worse projects, or necessitate less ambitious project scoping to ensure adequate completion, and I expect this remains broadly true through 4-6 years of study in most programs (don't take this as an endorsement of AI "assistants" for masters students; we've ignored a lot of other problems along the way).
There's a related problem: solving open-ended project assignments well ultimately depends on deeply understanding the problem, and AI "assistants" allow students to put a lot of code in their file without spending much time thinking about the problem or building an understanding of it. This is awful for learning outcomes, but also bad for project success. Getting students to see the value of thinking deeply about a problem is a thorny pedagogical puzzle at the best of times, and allowing the use of AI "assistants" makes the problem much much worse. This is another area I hope to see (or even drive) pedagogical improvement in, for what it's worth.
1/2

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
Wanyue Zhang, Yibin Huang, Yangbin Xu, JingJing Huang, Helu Zhi, Shuo Ren, Wang Xu, Jiajun Zhang
https://arxiv.org/abs/2509.02359

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
Spatial understanding is essential for Multimodal Large Language Models (MLLMs) to support perception, reasoning, and planning in embodied environments. Despite recent progress, existing studies reveal that MLLMs still struggle with spatial understanding. However, existing research lacks a comprehensive and systematic evaluation of these limitations, often restricted to isolated scenarios, such as single-view or video. In this work, we present a systematic analysis of spatial understanding from…

This https://arxiv.org/abs/2503.20117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
This work tackles the fundamental challenges in Federated Learning (FL) posed by arbitrary client participation and data heterogeneity, prevalent characteristics in practical FL settings. It is well-established that popular FedAvg-style algorithms struggle with exact convergence and can suffer from slow convergence rates since a decaying learning rate is required to mitigate these scenarios. To address these issues, we introduce the concept of stochastic matrix and the corresponding time-varyin…

💉 The ancient origins of the addiction-prone mind—and what it means for us today
#addiction

The ancient origins of the addiction-prone mind—and what it means for us today
Why do so many people struggle to stop drinking, quit smoking, or resist endless scrolling on their phones? Addiction touches millions of lives, yet it's often misunderstood as a personal weakness or moral failing. In reality, addiction is rooted in the ancient architecture of the human brain.

This https://arxiv.org/abs/2502.11753 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims
Misinformation can be countered with fact-checking, but the process is costly and slow. Identifying checkworthy claims is the first step, where automation can help scale fact-checkers' efforts. However, detection methods struggle with content that is (1) multimodal, (2) from diverse domains, and (3) synthetic. We introduce HintsOfTruth, a public dataset for multimodal checkworthiness detection with 27K real-world and synthetic image/claim pairs. The mix of real and synthetic data makes this dat…

Philippe Neau & Antonella Eye Porcelluzzi – Elephant
https://www.clongclongmoo.org/2025/06/05/philippe-neau-antonella-eye-porcelluzzi-elephant/

DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models
Shantanu Thorat, Andrew Caines
https://arxiv.org/abs/2508.00619 https://arxi…

DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models
Existing AIG (AI-generated) text detectors struggle in real-world settings despite succeeding in internal testing, suggesting that they may not be robust enough. We rigorously examine the machine-learning procedure to build these detectors to address this. Most current AIG text detection datasets focus on zero-shot generations, but little work has been done on few-shot or one-shot generations, where LLMs are given human texts as an example. In response, we introduce the Diverse Adversarial Corp…

This https://arxiv.org/abs/2505.16196 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

SEM: Enhancing Spatial Understanding for Robust Robot Manipulation
A key challenge in robot manipulation lies in developing policy models with strong spatial understanding, the ability to reason about 3D geometry, object relations, and robot embodiment. Existing methods often fall short: 3D point cloud models lack semantic abstraction, while 2D image encoders struggle with spatial reasoning. To address this, we propose SEM (Spatial Enhanced Manipulation model), a novel diffusion-based policy framework that explicitly enhances spatial understanding from two com…

Oh great, another newcomer asserting that fascism can be abolished through electoral means. As if electoralism changes anything, only the proletariat, through collective class struggle and revolutionary self-emancipation, can genuinely overthrow the capitalist system that sustains fascist and oppressive conditions.
#Fascism

This https://arxiv.org/abs/2506.02658 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Computational Thinking Reasoning in Large Language Models
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the root challenge is more profound: LLMs lack the complex thinking paradigms (\ie, computational thin…

Mark MacKinnon begleitet ukrainische Eliteeinheiten. Einige dienten zunächst in #Kabul und kämpften jetzt an zentralen Stellen, wie #Kyjiw, Asow-Stahl und anderen.
---
An elite squad of Ukrainian fighters has been battling Russian occupation on the front lines. This is the story of their war - The Glo…

This https://arxiv.org/abs/2501.14755 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
The burgeoning field of foundation models necessitates advanced data processing mechanisms capable of harnessing vast and valuable data with various types used by these models. Nevertheless, the current landscape presents unique challenges that traditional data processing frameworks struggle to handle effectively, particularly in handling the complexity of multimodal data. In response, we present Data-Juicer 2.0, a data processing system backed by 100+ data processing operators spanning text, i…

Automated Type Annotation in Python Using Large Language Models
Varun Bharti, Shashwat Jha, Dhruv Kumar, Pankaj Jalote
https://arxiv.org/abs/2508.00422 https://

Automated Type Annotation in Python Using Large Language Models
Type annotations in Python enhance maintainability and error detection. However, generating these annotations manually is error prone and requires extra effort. Traditional automation approaches like static analysis, machine learning, and deep learning struggle with limited type vocabularies, behavioral over approximation, and reliance on large labeled datasets. In this work, we explore the use of LLMs for generating type annotations in Python. We develop a generate check repair pipeline: the L…

This https://arxiv.org/abs/2503.06474 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

ROGRAG: A Robustly Optimized GraphRAG Framework
Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph for dynamic retrieval. However, existing pipelines involve complex engineering workflows, making it difficult to isolate the impact of individual components. It is also challenging to evaluate the retrieval effectiveness due to the overlap between the pretra…

Deep Self-knowledge Distillation: A hierarchical supervised learning for coronary artery segmentation
Mingfeng Lin
https://arxiv.org/abs/2509.03173 https://

Deep Self-knowledge Distillation: A hierarchical supervised learning for coronary artery segmentation
Coronary artery disease is a leading cause of mortality, underscoring the critical importance of precise diagnosis through X-ray angiography. Manual coronary artery segmentation from these images is time-consuming and inefficient, prompting the development of automated models. However, existing methods, whether rule-based or deep learning models, struggle with issues like poor performance and limited generalizability. Moreover, current knowledge distillation methods applied in this field have n…

Reactive Bottom-Up Testing
Siddharth Muralee, Sourag Cherupattamoolayil, James C. Davis, Antonio Bianchi, Aravind Machiry
https://arxiv.org/abs/2509.03711 https://

Reactive Bottom-Up Testing
Modern computing systems remain rife with software vulnerabilities. Engineers apply many means to detect them, of which dynamic testing is one of the most common and effective. However, most dynamic testing techniques follow a top-down paradigm, and struggle to reach and exercise functions deep within the call graph. While recent works have proposed Bottom-Up approaches to address these limitations, they face challenges with false positives and generating valid inputs that adhere to the context…

EchoLadder: Progressive AI-Assisted Design of Immersive VR Scenes
Zhuangze Hou, Jingze Tian, Nianlong Li, Farong Ren, Can Liu
https://arxiv.org/abs/2508.02173 https://

EchoLadder: Progressive AI-Assisted Design of Immersive VR Scenes
Mixed reality platforms allow users to create virtual environments, yet novice users struggle with both ideation and execution in spatial design. While existing AI models can automatically generate scenes based on user prompts, the lack of interactive control limits users' ability to iteratively steer the output. In this paper, we present EchoLadder, a novel human-AI collaboration pipeline that leverages large vision-language model (LVLM) to support interactive scene modification in virtual rea…

This https://arxiv.org/abs/2410.16428 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions
Modern speaker verification systems primarily rely on speaker embeddings and cosine similarity. While effective, these methods struggle with multi-talker speech due to the unidentifiability of embedding vectors. We propose Neural Scoring (NS), a novel end-to-end framework that directly estimates verification posterior probabilities without relying on test-side embeddings, making it more powerful and robust to complex conditions, e.g., with multiple talkers. To address the challenge of training …

From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
Yichao Feng
https://arxiv.org/abs/2508.02458 https://…

From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
Large Language Models show promise in emotion understanding, social reasoning, and empathy, yet they struggle with psychologically grounded tasks that require inferring implicit mental states in context-rich, ambiguous settings. These limitations arise from the absence of theory-aligned supervision and the difficulty of capturing nuanced mental processes in real-world narratives. To address this gap, we leverage expert-labeled, psychologically rich scenarios and propose a trajectory-aware reinf…

No real difference between the actions of the Israel regime and the Nazis, is there?
Unprecedented water crisis in Gaza amid Israeli-induced starvation | Israel-Palestine conflict News | Al Jazeera
https://www.aljazeera.com/gallery/2025/…

Unprecedented water crisis in Gaza amid Israeli-induced starvation
Israel’s war has destroyed Gaza’s water supplies, forcing residents to struggle daily for safe drinking water.

ModFus-DM: Explore the Representation in Modulated Signal Diffusion Generated Models
Haoyue Tan, Yu Li, Zhenxi Zhang, Xiaoran Shi, Feng Zhou
https://arxiv.org/abs/2508.01719 htt…

ModFus-DM: Explore the Representation in Modulated Signal Diffusion Generated Models
Automatic modulation classification (AMC) is essential for wireless communication systems in both military and civilian applications. However, existing deep learning-based AMC methods often require large labeled signals and struggle with non-fixed signal lengths, distribution shifts, and limited labeled signals. To address these challenges, we propose a modulation-driven feature fusion via diffusion model (ModFus-DM), a novel unsupervised AMC framework that leverages the generative capacity of …

This https://arxiv.org/abs/2503.16424 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGR_…

Bézier Splatting for Fast and Differentiable Vector Graphics Rendering
Differentiable vector graphics (VGs) are widely used in image vectorization and vector synthesis, while existing representations are costly to optimize and struggle to achieve high-quality rendering results for high-resolution images. This work introduces a new differentiable VG representation, dubbed Bézier Splatting, that enables fast yet high-fidelity VG rasterization. Bézier Splatting samples 2D Gaussians along Bézier curves, which naturally provide positional gradients at object boundar…

This https://arxiv.org/abs/2503.22733 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

RBFleX-NAS: Training-Free Neural Architecture Search Using Radial Basis Function Kernel and Hyperparameter Detection
Neural Architecture Search (NAS) is an automated technique to design optimal neural network architectures for a specific workload. Conventionally, evaluating candidate networks in NAS involves extensive training, which requires significant time and computational resources. To address this, training-free NAS has been proposed to expedite network evaluation with minimal search time. However, state-of-the-art training-free NAS algorithms struggle to precisely distinguish well-performing networks f…

Graph Neural Networks for Jamming Source Localization
Dania Herzalla, Willian T. Lunardi, Martin Andreoni
https://arxiv.org/abs/2506.03196 https://

Graph Neural Networks for Jamming Source Localization
Graph-based learning has emerged as a transformative approach for modeling complex relationships across diverse domains, yet its potential in wireless security remains largely unexplored. In this work, we introduce the first application of graph-based learning for jamming source localization, addressing the imminent threat of jamming attacks in wireless networks. Unlike geometric optimization techniques that struggle under environmental uncertainties and dense interference, we reformulate local…

Zero-Shot Anomaly Detection with Dual-Branch Prompt Learning
Zihan Wang, Samira Ebrahimi Kahou, Narges Armanfard
https://arxiv.org/abs/2508.00777 https://a…

Zero-Shot Anomaly Detection with Dual-Branch Prompt Learning
Zero-shot anomaly detection (ZSAD) enables identifying and localizing defects in unseen categories by relying solely on generalizable features rather than requiring any labeled examples of anomalies. However, existing ZSAD methods, whether using fixed or learned prompts, struggle under domain shifts because their training data are derived from limited training domains and fail to generalize to new distributions. In this paper, we introduce PILOT, a framework designed to overcome these challenge…

Rxiv-Maker: An Automated Template Engine for Streamlined Scientific Publications
Bruno M. Saraiva, Guillaume Jaquemet, Ricardo Henriques
https://arxiv.org/abs/2508.00836 https:/…

Rxiv-Maker: An Automated Template Engine for Streamlined Scientific Publications
Scientific publishing increasingly relies on preprint servers for rapid dissemination, yet researchers often struggle with manuscript preparation and quality control. Here we present Rxiv-Maker, a GitHub-native framework that converts markdown content to publication-ready PDFs through automated LaTeX processing. The system addresses reproducibility challenges in computational biology and imaging research by treating manuscripts as executable outputs rather than static documents. Rxiv-Maker inte…

This https://arxiv.org/abs/2505.23703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability
Enhancing the mathematical reasoning capabilities of LLMs has garnered significant attention in both the mathematical and computer science communities. Recent works have made substantial progress in both Natural Language (NL) reasoning and Formal Language (FL) reasoning by leveraging the potential of pure Reinforcement Learning (RL) methods on base models. However, RL approaches struggle to impart new capabilities not presented in the base model, highlighting the need to integrate more knowledg…

StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching
Chao Xue, Ziyuan Gao
https://arxiv.org/abs/2509.02033 https://arxiv.org…

StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching
Text semantic matching requires nuanced understanding of both structural relationships and fine-grained semantic distinctions. While pre-trained language models excel at capturing token-level interactions, they often overlook hierarchical structural patterns and struggle with subtle semantic discrimination. In this paper, we proposed StructCoh, a graph-enhanced contrastive learning framework that synergistically combines structural reasoning with representation space optimization. Our approach …

Machine Learning Classification of COSMOS2020 Galaxies: Quiescent vs. Star-Forming
Vahid Asadi, Nima Chartab, Akram Hasani Zonoozi, Hosein Haghi
https://arxiv.org/abs/2509.03039

Machine Learning Classification of COSMOS2020 Galaxies: Quiescent vs. Star-Forming
Accurately distinguishing between quiescent and star-forming galaxies is essential for understanding galaxy evolution. Traditional methods, such as spectral energy distribution (SED) fitting, can be computationally expensive and may struggle to capture complex galaxy properties. This study aims to develop a robust and efficient machine learning (ML) classification method to identify quiescent and star-forming galaxies within the Farmer COSMOS2020 catalog. We utilized JWST wide-field light cones…

A Dynamic Allocation Scheme for Adaptive Shared-Memory Mapping on Kilo-core RV Clusters for Attention-Based Model Deployment
Bowen Wang, Marco Bertuletti, Yichao Zhang, Victor J. B. Jung, Luca Benini
https://arxiv.org/abs/2508.01180

A Dynamic Allocation Scheme for Adaptive Shared-Memory Mapping on Kilo-core RV Clusters for Attention-Based Model Deployment
Attention-based models demand flexible hardware to manage diverse kernels with varying arithmetic intensities and memory access patterns. Large clusters with shared L1 memory, a common architectural pattern, struggle to fully utilize their processing elements (PEs) when scaled up due to reduced throughput in the hierarchical PE-to-L1 intra-cluster interconnect. This paper presents Dynamic Allocation Scheme (DAS), a runtime programmable address remapping hardware unit coupled with a unified memo…

This https://arxiv.org/abs/2503.19449 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations
Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-sp…

Collimated QED Cascades with Curved Plasma Mirror
Xuesong Geng, M. A. Serebryakov, E. N. Nerush, A. S. Samsonov, I. Y. Kostyukov, Liangliang Ji
https://arxiv.org/abs/2508.00417 …

Collimated QED Cascades with Curved Plasma Mirror
Converting light into matter has been a longstanding goal in physics, particularly the creation of electron-positron pairs through quantum electrodynamic (QED) processes. While current approaches using multiple colliding laser pulses can achieve this conversion, they struggle to produce well-collimated particle beams - a crucial requirement for practical applications. Here we demonstrate that a single ultra-intense laser pulse, when reflected from a curved plasma mirror, can generate highly col…

Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection
David Hirnschall
https://arxiv.org/abs/2509.00931 https://

Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection
We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as time series classification task. As financial transaction data streams grow in scale and complexity, traditional methods often require large labeled datasets, struggle with time series of irregular sampling frequencies and varying sequence lengths. To address these challenges, we extend conditional Generative Adversarial Networks (GANs) for targeted data augmentation, integrate Bayesian i…

This https://arxiv.org/abs/2504.12423 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Benchmarking Audio Deepfake Detection Robustness in Real-world Communication Scenarios
Existing Audio Deepfake Detection (ADD) systems often struggle to generalise effectively due to the significantly degraded audio quality caused by audio codec compression and channel transmission effects in real-world communication scenarios. To address this challenge, we developed a rigorous benchmark to evaluate the performance of the ADD system under such scenarios. We introduced ADD-C, a new test dataset to evaluate the robustness of ADD systems under diverse communication conditions, inclu…

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

Generalizing Unsupervised Lidar Odometry Model from Normal to Snowy Weather Conditions
Beibei Zhou, Zhiyuan Zhang, Zhenbo Song, Jianhui Guo, Hui Kong
https://arxiv.org/abs/2509.02011

Generalizing Unsupervised Lidar Odometry Model from Normal to Snowy Weather Conditions
Deep learning-based LiDAR odometry is crucial for autonomous driving and robotic navigation, yet its performance under adverse weather, especially snowfall, remains challenging. Existing models struggle to generalize across conditions due to sensitivity to snow-induced noise, limiting real-world use. In this work, we present an unsupervised LiDAR odometry model to close the gap between clear and snowy weather conditions. Our approach focuses on effective denoising to mitigate the impact of snow…

Intense battles continue as Russian forces struggle to advance in Ukraine's Sumy and Pokrovsk regions: https://benborges.xyz/2025/06/30/intense-battles-continue-as-russian.html

Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
Fangzhou Wu, Sandeep Silwal
https://arxiv.org/abs/2509.02718 https://arxiv.org/pdf…

Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving
Increasing demand for Large Language Models (LLMs) services imposes substantial deployment and computation costs on providers. LLM routing offers a cost-efficient solution by directing queries to the optimal LLM based on model and query features. However, existing works primarily focus on offline scenarios and struggle to adapt to online settings with high query volume and constrained token budgets. In this work, we introduce the first training-free algorithm for online routing scenarios. Our a…

Enhancing Text Comprehension for Dyslexic Readers: A 3D Semantic Visualization Approach Using Transformer Mode
Zhengyang Li
https://arxiv.org/abs/2506.03731

Enhancing Text Comprehension for Dyslexic Readers: A 3D Semantic Visualization Approach Using Transformer Mode
Dyslexic individuals often face significant challenges with traditional reading, particularly when engaging with complex texts such as mystery novels. These texts typically demand advanced narrative tracking and information integration skills, making it difficult for dyslexic readers to fully comprehend the content. However, research indicates that while dyslexic individuals may struggle with textual processing, they often possess strong spatial imagination abilities. Leveraging this strength, …

PianoBind: A Multimodal Joint Embedding Model for Pop-piano Music
Hayeon Bang, Eunjin Choi, Seungheon Doh, Juhan Nam
https://arxiv.org/abs/2509.04215 https://

PianoBind: A Multimodal Joint Embedding Model for Pop-piano Music
Solo piano music, despite being a single-instrument medium, possesses significant expressive capabilities, conveying rich semantic information across genres, moods, and styles. However, current general-purpose music representation models, predominantly trained on large-scale datasets, often struggle to captures subtle semantic distinctions within homogeneous solo piano music. Furthermore, existing piano-specific representation models are typically unimodal, failing to capture the inherently mul…

Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval
Anuraj Maurya
https://arxiv.org/abs/2509.00141 https://

Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval
The rapid growth of statutory corpora and judicial decisions requires scalable legal AI systems capable of classification and retrieval over extremely long contexts. Transformer-based architectures (e.g., Longformer, DeBERTa) dominate current legal NLP benchmarks but struggle with quadratic attention costs, limiting efficiency and scalability. In this work, we present the first comprehensive benchmarking of Mamba, a state-space model (SSM) with linear-time selective mechanisms, against leading …

AI bots playing music for other bots. A signpost along the way to our Matrix-like future
https://futurism.com/ai-band-spotify-streams

An "Indie Rock Band" That Appears to Be Entirely AI-Generated Is Making Alarming Amounts of Money on Spotify
While real artists struggle to earn money on Spotify, a seemingly AI-generated band has garnered enough streams to actually make a buck. 

SWAN: Synergistic Wavelet-Attention Network for Infrared Small Target Detection
Yuxin Jing, Jufeng Zhao, Tianpei Zhang, Yiming Zhu
https://arxiv.org/abs/2508.01322 https://

SWAN: Synergistic Wavelet-Attention Network for Infrared Small Target Detection
Infrared small target detection (IRSTD) is thus critical in both civilian and military applications. This study addresses the challenge of precisely IRSTD in complex backgrounds. Recent methods focus fundamental reliance on conventional convolution operations, which primarily capture local spatial patterns and struggle to distinguish the unique frequency-domain characteristics of small targets from intricate background clutter. To overcome these limitations, we proposed the Synergistic Wavelet-…

Statistics-Friendly Confidentiality Protection for Establishment Data, with Applications to the QCEW
Kaitlyn Webb, Prottay Protivash, John Durrell, Daniell Toth, Aleksandra Slavkovi\'c, Daniel Kifer
https://arxiv.org/abs/2509.01597

Statistics-Friendly Confidentiality Protection for Establishment Data, with Applications to the QCEW
Confidentiality for business data is an understudied area of disclosure avoidance, where legacy methods struggle to provide acceptable results. Modern formal privacy techniques designed for person-level data do not provide suitable confidentiality/utility trade-offs due to the highly skewed nature of business data and because extreme outlier records are often important contributors to query answers. In this paper, inspired by Gaussian Differential Privacy, we propose a novel confidentiality fra…

This https://arxiv.org/abs/2505.04670 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

LLM Code Customization with Visual Results: A Benchmark on TikZ
With the rise of AI-based code generation, customizing existing code out of natural language instructions to modify visual results -such as figures or images -has become possible, promising to reduce the need for deep programming expertise. However, even experienced developers can struggle with this task, as it requires identifying relevant code regions (feature location), generating valid code variants, and ensuring the modifications reliably align with user intent. In this paper, we introduce…

Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
Lydia Kin Ching Chau, Zhi Yu, Ruo Wei Jiang
https://arxiv.org/abs/2509.02445 ht…

Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
We present a novel framework for real-time virtual makeup try-on that achieves high-fidelity, identity-preserving cosmetic transfer with robust temporal consistency. In live makeup transfer applications, it is critical to synthesize temporally coherent results that accurately replicate fine-grained makeup and preserve user's identity. However, existing methods often struggle to disentangle semitransparent cosmetics from skin tones and other identify features, causing identity shifts and raising…

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
Shanglin Wu, Lihui Liu, Jinho D. Choi, Kai Shu
https://arxiv.org/abs/2509.03540 https://

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) methods address this issue by incorporating external knowledge from trusted sources at inference time. However, such methods typically treat knowledge as unstructured text, which limits their ability to support compositional reasoning and identify factual inconsistencies. To overcome these limitations, we propose a novel fram…

Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
Fleur Hendriks, Ond\v{r}ej Roko\v{s}, Martin Do\v{s}k\'a\v{r}, Marc G. D. Geers, Vlado Menkovski
https://arxiv.org/abs/2509.03340

Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
Bifurcation phenomena in nonlinear dynamical systems often lead to multiple coexisting stable solutions, particularly in the presence of symmetry breaking. Deterministic machine learning models struggle to capture this multiplicity, averaging over solutions and failing to represent lower-symmetry outcomes. In this work, we propose a generative framework based on flow matching to model the full probability distribution over bifurcation outcomes. Our method enables direct sampling of multiple val…

EEG-MSAF: An Interpretable Microstate Framework uncovers Default-Mode Decoherence in Early Neurodegeneration
Mohammad Mehedi Hasan, Pedro G. Lind, Hernando Ombao, Anis Yazidi, Rabindra Khadka
https://arxiv.org/abs/2509.02568

EEG-MSAF: An Interpretable Microstate Framework uncovers Default-Mode Decoherence in Early Neurodegeneration
Dementia (DEM) is a growing global health challenge, underscoring the need for early and accurate diagnosis. Electroencephalography (EEG) provides a non-invasive window into brain activity, but conventional methods struggle to capture its transient complexity. We present the \textbf{EEG Microstate Analysis Framework (EEG-MSAF)}, an end-to-end pipeline that leverages EEG microstates discrete, quasi-stable topographies to identify DEM-related biomarkers and distinguish DEM, mild cognitive impairm…

AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Models
Chenhao Xue, Kezhi Li, Jiaxing Zhang, Yi Ren, Zhengyuan Shi, Chen Zhang, Yibo Lin, Lining Zhang, Qiang Xu, Guangyu Sun
https://arxiv.org/abs/2507.02598

AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Models
Arithmetic circuits, such as adders and multipliers, are fundamental components of digital systems, directly impacting the performance, power efficiency, and area footprint. However, optimizing these circuits remains challenging due to the vast design space and complex physical constraints. While recent deep learning-based approaches have shown promise, they struggle to consistently explore high-potential design variants, limiting their optimization efficiency. To address this challenge, we pro…

CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates
Shuchang Liu, Paul A. O'Gorman
https://arxiv.org/abs/2509.00010 https://

CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates
Robust generalization under climate change remains a major challenge for machine learning applications in climate science. Most existing approaches struggle to extrapolate beyond the climate they were trained on, leading to a strong dependence on training data from model simulations of warm climates. Use of climate-invariant inputs improves generalization but requires challenging manual feature engineering. Here, we present CERA (Climate-invariant Encoding through Representation Alignment), a m…

PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
Jiajun He, Naoki Sawada, Koichi Miyazaki, Tomoki Toda
https://arxiv.org/abs/2509.04357 https…

PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-grained phoneme variations due to limited entity diversity. Moreover, prior methods treat entities as independent tokens, leading to incomplete multi-token biasing. To address these issues, we propose Phoneme-Augmented Robust Contextual ASR via COntrastive entity disambiguation (PARCO), which integrates phoneme-aware …

Earthquake Source Depth Determination using Single Station Waveforms and Deep Learning
Wenda Li, Miao Zhang
https://arxiv.org/abs/2509.02346 https://arxiv.…

Earthquake Source Depth Determination using Single Station Waveforms and Deep Learning
In areas with limited station coverage, earthquake depth constraints are much less accurate than their latitude and longitude. Traditional travel-time-based location methods struggle to constrain depths due to imperfect station distribution and the strong trade-off between source depth and origin time. Identifying depth phases at regional distances is usually hindered by strong wave scattering, which is particularly challenging for low-magnitude events. Deep learning algorithms, capable of extr…

Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network
Athanasios Tziouvaras, Carolina Fortuna, George Floros, Kostas Kolomvatsos, Panagiotis Sarigiannidis, Marko Grobelnik, Bla\v{z} Bertalani\v{c}
https://arxiv.org/abs/2508.00042

Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network
AI-native 6G networks promise unprecedented automation and performance by embedding machine-learning models throughout the radio access and core segments of the network. However, the non-stationary nature of wireless environments due to infrastructure changes, user mobility, and emerging traffic patterns, induces concept drifts that can quickly degrade these model accuracies. Existing methods in general are very domain specific, or struggle with certain type of concept drift. In this paper, we …

PBS, NPR stations struggle with Trump-fueled government funding cuts (David Bauder/Associated Press)
https://apnews.com/article/npr-pbs-public-broadcasting-trump-cuts-73de8fadf32655aa74752690d22a3758
http://www.memeorandum.com/250831/p104#a250831p104

IL-SLAM: Intelligent Line-assisted SLAM Based on Feature Awareness for Dynamic Environments
Haolan Zhang, Thanh Nguyen Canh, Chenghao Li, Ruidong Yang, Yonghoon Ji, Nak Young Chong
https://arxiv.org/abs/2509.02972

IL-SLAM: Intelligent Line-assisted SLAM Based on Feature Awareness for Dynamic Environments
Visual Simultaneous Localization and Mapping (SLAM) plays a crucial role in autonomous systems. Traditional SLAM methods, based on static environment assumptions, struggle to handle complex dynamic environments. Recent dynamic SLAM systems employ geometric constraints and deep learning to remove dynamic features, yet this creates a new challenge: insufficient remaining point features for subsequent SLAM processes. Existing solutions address this by continuously introducing additional line and p…

VChatter: Exploring Generative Conversational Agents for Simulating Exposure Therapy to Reduce Social Anxiety
Han Zhang, KaWing Tsang, Zhenhui Peng
https://arxiv.org/abs/2506.03520

VChatter: Exploring Generative Conversational Agents for Simulating Exposure Therapy to Reduce Social Anxiety
Many people struggle with social anxiety, feeling fear, or even physically uncomfortable in social situations like talking to strangers. Exposure therapy, a clinical method that gradually and repeatedly exposes individuals to the source of their fear and helps them build coping mechanisms, can reduce social anxiety but traditionally requires human therapists' guidance and constructions of situations. In this paper, we developed a multi-agent system VChatter to explore large language models(LLMs…

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Yuansheng Ni, Ping Nie, Kai Zou, Xiang Yue, Wenhu Chen
https://arxiv.org/abs/2506.03930

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded supervision and offer limited support for iterative code correction, resulting in fragile and unreliable plot generation. We present VisCode-200K, a large-scale instruction tuning dataset for Python-based visualization and self-correction. It contains over 200K exampl…

Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion
Zeren Xiong, Zikun Chen, Zedong Zhang, Xiang Li, Ying Tai, Jian Yang, Jun Li
https://arxiv.org/abs/2509.02357

Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion
In this paper, we tackle a new task of 3D object synthesis, where a 3D model is composited with another object category to create a novel 3D model. However, most existing text/image/3D-to-3D methods struggle to effectively integrate multiple content sources, often resulting in inconsistent textures and inaccurate shapes. To overcome these challenges, we propose a straightforward yet powerful approach, category+3D-to-3D (C33D), for generating novel and structurally coherent 3D models. Our method…

Social World Models
Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap
https://arxiv.org/abs/2509.00559 https://arxiv.org/pdf/2509.00559

Social World Models
Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions …

A Diffusion-Driven Temporal Super-Resolution and Spatial Consistency Enhancement Framework for 4D MRI imaging
Xuanru Zhou, Jiarun Liu, Shoujun Yu, Hao Yang, Cheng Li, Tao Tan, Shanshan Wang
https://arxiv.org/abs/2506.04116

A Diffusion-Driven Temporal Super-Resolution and Spatial Consistency Enhancement Framework for 4D MRI imaging
In medical imaging, 4D MRI enables dynamic 3D visualization, yet the trade-off between spatial and temporal resolution requires prolonged scan time that can compromise temporal fidelity--especially during rapid, large-amplitude motion. Traditional approaches typically rely on registration-based interpolation to generate intermediate frames. However, these methods struggle with large deformations, resulting in misregistration, artifacts, and diminished spatial consistency. To address these chall…

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
Anum Afzal, Juraj Vladika, Florian Matthes
https://arxiv.org/abs/2509.02198

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
Large Language Models tend to struggle when dealing with specialized domains. While all aspects of evaluation hold importance, factuality is the most critical one. Similarly, reliable fact-checking tools and data sources are essential for hallucination mitigation. We address these issues by providing a comprehensive Fact-checking Benchmark FActBench covering four generation tasks and six state-of-the-art Large Language Models (LLMs) for the Medical domain. We use two state-of-the-art Fact-check…

A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations
Petr Grinberg, Ankur Kumar, Surya Koppisetti, Gaurav Bharaj
https://arxiv.org/abs/2506.03425

A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations
Evaluating explainability techniques, such as SHAP and LRP, in the context of audio deepfake detection is challenging due to lack of clear ground truth annotations. In the cases when we are able to obtain the ground truth, we find that these methods struggle to provide accurate explanations. In this work, we propose a novel data-driven approach to identify artifact regions in deepfake audio. We consider paired real and vocoded audio, and use the difference in time-frequency representation as th…

TacMan-Turbo: Proactive Tactile Control for Robust and Efficient Articulated Object Manipulation
Zihang Zhao, Zhenghao Qi, Yuyang Li, Leiyao Cui, Zhi Han, Lecheng Ruan, Yixin Zhu
https://arxiv.org/abs/2508.02204

TacMan-Turbo: Proactive Tactile Control for Robust and Efficient Articulated Object Manipulation
Adept manipulation of articulated objects is essential for robots to operate successfully in human environments. Such manipulation requires both effectiveness -- reliable operation despite uncertain object structures -- and efficiency -- swift execution with minimal redundant steps and smooth actions. Existing approaches struggle to achieve both objectives simultaneously: methods relying on predefined kinematic models lack effectiveness when encountering structural variations, while tactile-inf…

Improving Narrative Classification and Explanation via Fine Tuned Language Models
Rishit Tyagi, Rahul Bouri, Mohit Gupta
https://arxiv.org/abs/2509.04077 https://

Improving Narrative Classification and Explanation via Fine Tuned Language Models
Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predi…

Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution
Xiaobao Wei, Changyong Shu, Zhaokun Yue, Chang Huang, Weiwei Liu, Shuai Yang, Lirong Yang, Peng Gao, Wenbin Zhang, Gaochao Zhu, Chengxiang Wang
https://arxiv.org/abs/2509.02415

Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution
High-performance real-time stereo matching methods invariably rely on 3D regularization of the cost volume, which is unfriendly to mobile devices. And 2D regularization based methods struggle in ill-posed regions. In this paper, we present a deployment-friendly 4D cost aggregation network DBStereo, which is based on pure 2D convolutions. Specifically, we first provide a thorough analysis of the decoupling characteristics of 4D cost volume. And design a lightweight bidirectional geometry aggrega…

HERCULES: Hardware accElerator foR stoChastic schedULing in hEterogeneous Systems
Vairavan Palaniappan, Adam H. Ross, Amit Ranjan Trivedi, Debjit Pal
https://arxiv.org/abs/2507.01113

HERCULES: Hardware accElerator foR stoChastic schedULing in hEterogeneous Systems
Efficient workload scheduling is a critical challenge in modern heterogeneous computing environments, particularly in high-performance computing (HPC) systems. Traditional software-based schedulers struggle to efficiently balance workload distribution due to high scheduling overhead, lack of adaptability to dynamic workloads, and suboptimal resource utilization. These pitfalls are compounded in heterogeneous systems, where differing computational elements can have vastly different performance p…

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Fatih Pehlivan, Ar\c{c}in \"Ulk\"u Erg\"uzen, Sahand Moslemi Yengejeh, Mayasah Lami, Anil Koyuncu
https://arxiv.org/abs/2509.03093

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically focus on individual SOLID principles or specific programming languages, leaving a gap in the ability to detect violations across all five principles in multi-language codebases. This paper presents a new approach: a methodology that leverages tailored prompt e…

CMRAG: Co-modality-based document retrieval and visual question answering
Wang Chen, Guanqiang Qi, Weikang Li, Yang Li
https://arxiv.org/abs/2509.02123 https://

CMRAG: Co-modality-based document retrieval and visual question answering
Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and text extraction, which can only utilize explicit text information and struggle to capture images or unstructured content; the other category treats document segmentation as visual input and directly passes it to visual language models (VLMs) for processing, ye…

MISC: Minimal Intervention Shared Control with Guaranteed Safety under Non-Convex Constraints
Shivam Chaubey, Francesco Verdoja, Shankar Deka, Ville Kyrki
https://arxiv.org/abs/2507.02438

MISC: Minimal Intervention Shared Control with Guaranteed Safety under Non-Convex Constraints
Shared control combines human intention with autonomous decision-making, from low-level safety overrides to high-level task guidance, enabling systems that adapt to users while ensuring safety and performance. This enhances task effectiveness and user experience across domains such as assistive robotics, teleoperation, and autonomous driving. However, existing shared control methods, based on e.g. Model Predictive Control, Control Barrier Functions, or learning-based control, struggle with feas…

Quantum-inspired probability metrics define a complete, universal space for statistical learning
Logan S. McCarty
https://arxiv.org/abs/2508.21086 https://…

Quantum-inspired probability metrics define a complete, universal space for statistical learning
Comparing probability distributions is a core challenge across the natural, social, and computational sciences. Existing methods, such as Maximum Mean Discrepancy (MMD), struggle in high-dimensional and non-compact domains. Here we introduce quantum probability metrics (QPMs), derived by embedding probability measures in the space of quantum states: positive, unit-trace operators on a Hilbert space. This construction extends kernel-based methods and overcomes the incompleteness of MMD on non-co…

NoteBar: An AI-Assisted Note-Taking System for Personal Knowledge Management
Josh Wisoff, Yao Tang, Zhengyu Fang, Jordan Guzman, YuTang Wang, Alex Yu
https://arxiv.org/abs/2509.03610

NoteBar: An AI-Assisted Note-Taking System for Personal Knowledge Management
Note-taking is a critical practice for capturing, organizing, and reflecting on information in both academic and professional settings. The recent success of large language models has accelerated the development of AI-assisted tools, yet existing solutions often struggle with efficiency. We present NoteBar, an AI-assisted note-taking tool that leverages persona information and efficient language models to automatically organize notes into multiple categories and better support user workflows. T…

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
Luca Cotti, Anisa Rula, Devis Bianchini, Federico Cerutti
https://arxiv.org/abs/2509.00081

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and transparently, particularly in cases involving unstructured or ambiguous log entries. In this work, we propose a novel methodology that combines ontology-driven structured outputs with Large Language Models (LLMs), to build an Artificial Int…

Precisely Detecting Python Type Errors via LLM-based Unit Test Generation
Chen Yang, Ziqi Wang, Yanjie Jiang, Lin Yang, Yuteng Zheng, Jianyi Zhou, Junjie Chen
https://arxiv.org/abs/2507.02318

Precisely Detecting Python Type Errors via LLM-based Unit Test Generation
Type errors in Python often lead to runtime failures, posing significant challenges to software reliability and developer productivity. Existing static analysis tools aim to detect such errors without execution but frequently suffer from high false positive rates. Recently, unit test generation techniques offer great promise in achieving high test coverage, but they often struggle to produce bug-revealing tests without tailored guidance. To address these limitations, we present RTED, a novel ty…

DRetNet: A Novel Deep Learning Framework for Diabetic Retinopathy Diagnosis
Idowu Paul Okuwobi, Jingyuan Liu, Jifeng Wan, Jiaojiao Jiang
https://arxiv.org/abs/2509.01072 https:/…

DRetNet: A Novel Deep Learning Framework for Diabetic Retinopathy Diagnosis
Diabetic retinopathy (DR) is a leading cause of blindness worldwide, necessitating early detection to prevent vision loss. Current automated DR detection systems often struggle with poor-quality images, lack interpretability, and insufficient integration of domain-specific knowledge. To address these challenges, we introduce a novel framework that integrates three innovative contributions: (1) Adaptive Retinal Image Enhancement Using Physics-Informed Neural Networks (PINNs): this technique dyna…

Enhanced Fingerprint-based Positioning With Practical Imperfections: Deep learning-based approaches
Shugong Xu, Jun Jiang, Wenjun Yu, Yilin Gao, Guangjin Pan, Shiyi Mu, Zhiqi Ai, Yuan Gao, Peigang Jiang, Cheng-Xiang Wang
https://arxiv.org/abs/2509.01197

Enhanced Fingerprint-based Positioning With Practical Imperfections: Deep learning-based approaches
High-precision positioning is vital for cellular networks to support innovative applications such as extended reality, unmanned aerial vehicles (UAVs), and industrial Internet of Things (IoT) systems. Existing positioning algorithms using deep learning techniques require vast amounts of labeled data, which are difficult to obtain in real-world cellular environments, and these models often struggle to generalize effectively. To advance cellular positioning techniques, the 2024 Wireless Communica…

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
https://arxiv.org/abs/2509.02510

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in open-ended text generation: fostering diversity and creativity while preserving logical coherence. Existing truncated sampling techniques, including temperature scaling, top-\$p\$ (nucleus) sampling, and min-\$p\$ sampling, aim to manage this trade-off. However, they exhibit limitations, particularly in the effective incorporation of the confiden…

Formal Bayesian Transfer Learning via the Total Risk Prior
Nathan Wycoff, Ali Arab, Lisa O. Singh
https://arxiv.org/abs/2507.23768 https://arxiv.org/pdf/25…

Formal Bayesian Transfer Learning via the Total Risk Prior
In analyses with severe data-limitations, augmenting the target dataset with information from ancillary datasets in the application domain, called source datasets, can lead to significantly improved statistical procedures. However, existing methods for this transfer learning struggle to deal with situations where the source datasets are also limited and not guaranteed to be well-aligned with the target dataset. A typical strategy is to use the empirical loss minimizer on the source data as a pr…

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, Wen Zhang
https://arxiv.org/abs/2509.03995

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error propagation in decomposition frameworks. We propose RTQA, a novel framework to address these challenges by enhancing reasoning over TKGs without requiring training. Following recursive thinking, RTQA recursively decomposes questions into sub-problems, solves …

Adaptive Heavy-Tailed Stochastic Gradient Descent
Bodu Gong, Gustavo Enrique Batista, Pierre Lafaye de Micheaux
https://arxiv.org/abs/2508.21353 https://ar…

Adaptive Heavy-Tailed Stochastic Gradient Descent
In the era of large-scale neural network models, optimization algorithms often struggle with generalization due to an overreliance on training loss. One key insight widely accepted in the machine learning community is the idea that wide basins (regions around a local minimum where the loss increases gradually) promote better generalization by offering greater stability to small changes in input data or model parameters. In contrast, sharp minima are typically more sensitive and less stable. Mot…

FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field
Fan Zhu, Yifan Zhao, Ziyu Chen, Biao Yu, Hui Zhu
https://arxiv.org/abs/2509.01547 https://

FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field
Visual SLAM has regained attention due to its ability to provide perceptual capabilities and simulation test data for Embodied AI. However, traditional SLAM methods struggle to meet the demands of high-quality scene reconstruction, and Gaussian SLAM systems, despite their rapid rendering and high-quality mapping capabilities, lack effective pose optimization methods and face challenges in geometric reconstruction. To address these issues, we introduce FGO-SLAM, a Gaussian SLAM system that emplo…

Generalizing Verifiable Instruction Following
Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, Hannaneh Hajishirzi
https://arxiv.org/abs/2507.02833

Generalizing Verifiable Instruction Following
A crucial factor for successful human and AI interaction is the ability of language models or chatbots to follow human instructions precisely. A common feature of instructions are output constraints like ``only answer with yes or no" or ``mention the word `abrakadabra' at least 3 times" that the user adds to craft a more useful answer. Even today's strongest models struggle with fulfilling such constraints. We find that most models strongly overfit on a small set of verifiable constraints from …

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Qingdong He, Xueqin Chen, Chaoyi Wang, Yanjie Pan, Xiaobin Hu, Zhenye Gan, Yabiao Wang, Chengjie Wang, Xiangtai Li, Jiangning Zhang
https://arxiv.org/abs/2507.01908

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving, or swapping objects. They struggle to handle more complex implicit hypothetical instructions that require deeper reasoning to infer plausible visual changes and user intent. Additionally, current datasets provide limited support for training and evaluating rea…

Automated Label Placement on Maps via Large Language Models
Harry Shomer, Jiejun Xu
https://arxiv.org/abs/2507.22952 https://arxiv.org/pdf/2507.22952

Automated Label Placement on Maps via Large Language Models
Label placement is a critical aspect of map design, serving as a form of spatial annotation that directly impacts clarity and interpretability. Despite its importance, label placement remains largely manual and difficult to scale, as existing automated systems struggle to integrate cartographic conventions, adapt to context, or interpret labeling instructions. In this work, we introduce a new paradigm for automatic label placement (ALP) that formulates the task as a data editing problem and lev…

Resting-state fMRI Analysis using Quantum Time-series Transformer
Junghoon Justin Park, Jungwoo Seo, Sangyoon Bae, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Jiook Cha, Shinjae Yoo
https://arxiv.org/abs/2509.00711

Resting-state fMRI Analysis using Quantum Time-series Transformer
Resting-state functional magnetic resonance imaging (fMRI) has emerged as a pivotal tool for revealing intrinsic brain network connectivity and identifying neural biomarkers of neuropsychiatric conditions. However, classical self-attention transformer models--despite their formidable representational power--struggle with quadratic complexity, large parameter counts, and substantial data requirements. To address these barriers, we introduce a Quantum Time-series Transformer, a novel quantum-enha…

DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
Xuan Hou, Shuhan Liu, Zhaohui Peng, Yaohui Chu, Yue Zhang, Yining Wang
https://arxiv.org/abs/2508.21340

DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
Time series synthesis is an effective approach to ensuring the secure circulation of time series data. Existing time series synthesis methods typically perform temporal modeling based on random sequences to generate target sequences, which often struggle to ensure the temporal dependencies in the generated time series. Additionally, directly modeling temporal features on random sequences makes it challenging to accurately capture the feature information of the original time series. To address t…

MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation
Zhenyu Wu, Angyuan Ma, Xiuwei Xu, Hang Yin, Yinan Liang, Ziwei Wang, Jiwen Lu, Haibin Yan
https://arxiv.org/abs/2509.01658

MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation
Mobile manipulation stands as a core challenge in robotics, enabling robots to assist humans across varied tasks and dynamic daily environments. Conventional mobile manipulation approaches often struggle to generalize across different tasks and environments due to the lack of large-scale training. However, recent advances in manipulation foundation models demonstrate impressive generalization capability on a wide range of fixed-base manipulation tasks, which are still limited to a fixed setting…

Active Learning for Forecasting Severity among Patients with Post Acute Sequelae of SARS-CoV-2
Jing Wang, Amar Sra, Jeremy C. Weiss
https://arxiv.org/abs/2506.22444

Active Learning for Forecasting Severity among Patients with Post Acute Sequelae of SARS-CoV-2
The long-term effects of Postacute Sequelae of SARS-CoV-2, known as PASC, pose a significant challenge to healthcare systems worldwide. Accurate identification of progression events, such as hospitalization and reinfection, is essential for effective patient management and resource allocation. However, traditional models trained on structured data struggle to capture the nuanced progression of PASC. In this study, we introduce the first publicly available cohort of 18 PASC patients, with text t…

Moment Sampling in Video LLMs for Long-Form Video QA
Mustafa Chasmai, Gauri Jagatap, Gouthaman KV, Grant Van Horn, Subhransu Maji, Andrea Fanelli
https://arxiv.org/abs/2507.00033 …

Moment Sampling in Video LLMs for Long-Form Video QA
Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on short videos, they often struggle with long-range reasoning in longer videos. To scale Video LLMs for longer video content, frame sub-sampling (selecting frames at regular intervals) is commonly used. However, this approach is suboptimal, often leading to the loss of crucial frames or the inclusion of redundant inform…

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Xinrun Xu, Jianwen Yang, Qiuhong Zhang, Zhanbiao Lian, Zhiming Ding, Shan Jiang
https://arxiv.org/abs/2507.00042

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Continually adapting edge models in cloud-edge collaborative object detection for traffic monitoring suffers from catastrophic forgetting, where models lose previously learned knowledge when adapting to new data distributions. This is especially problematic in dynamic traffic environments characterised by periodic variations (e.g., day/night, peak hours), where past knowledge remains valuable. Existing approaches like experience replay and visual prompts offer some mitigation, but struggle to e…

Online Human Action Detection during Escorting
Siddhartha Mondal, Avik Mitra, Chayan Sarkar
https://arxiv.org/abs/2506.23573 https://…

Online Human Action Detection during Escorting
The deployment of robot assistants in large indoor spaces has seen significant growth, with escorting tasks becoming a key application. However, most current escorting robots primarily rely on navigation-focused strategies, assuming that the person being escorted will follow without issue. In crowded environments, this assumption often falls short, as individuals may struggle to keep pace, become obstructed, get distracted, or need to stop unexpectedly. As a result, conventional robotic systems…

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…

Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation
Ronan Docherty, Antonis Vamvakeros, Samuel J. Cooper
https://arxiv.org/abs/2508.21529

Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation
Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are often patch-based, and so struggle to represent the fine features often present in micrographs; they also struggle with the large image sizes present in materials and biological image analysis. In this work, we train a convolutional neural network to upsample lo…

Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
Fatih Erdo\u{g}an, Merve Rabia Bar{\i}n, Fatma G\"uney
https://arxiv.org/abs/2508.21689 https://

Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
Constructing high-definition (HD) maps from sensory input requires accurately mapping the road elements in image space to the Bird's Eye View (BEV) space. The precision of this mapping directly impacts the quality of the final vectorized HD map. Existing HD mapping approaches outsource the projection to standard mapping techniques, such as attention-based ones. However, these methods struggle with accuracy due to generalization problems, often hallucinating non-existent road elements. Our key i…

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
Jessica Bader, Leander Girrbach, Stephan Alaniz, Zeynep Akata
https://arxiv.org/abs/2507.23784 https:/…

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
Concept Bottleneck Models (CBMs) and other concept-based interpretable models show great promise for making AI applications more transparent, which is essential in fields like medicine. Despite their success, we demonstrate that CBMs struggle to reliably identify the correct concepts under distribution shifts. To assess the robustness of CBMs to concept variations, we introduce SUB: a fine-grained image and concept benchmark containing 38,400 synthetic images based on the CUB dataset. To create…

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…