Tootfinder

Q&A with Pavel Durov on Telegram, his arrest, censorship, not using a phone, Romanian elections, VK, encryption, Edward Snowden, spring 2018 poisoning, and more (Lex Fridman)
https://lexfridman.com/pavel-durov-transcript

Navigating A Government Shutdown: One-Stop Resource Page (Congressman Jamie Raskin)
https://raskin.house.gov/2025/10/navigating-a-government-shutdown-one-stop-resource-page
http://www.memeorandum.com/251001/p6#a251001p6

did Dependabot take GitHub’s macOS down? ;)
https://www.githubstatus.com/incidents/071h21gptcp0

Degraded Performance for GitHub Actions MacOS Runners
GitHub's Status Page - Degraded Performance for GitHub Actions MacOS Runners.

EditTrack: Detecting and Attributing AI-assisted Image Editing
Zhengyuan Jiang, Yuyang Zhang, Moyang Guo, Neil Zhenqiang Gong
https://arxiv.org/abs/2510.01173 https://

EditTrack: Detecting and Attributing AI-assisted Image Editing
In this work, we formulate and study the problem of image-editing detection and attribution: given a base image and a suspicious image, detection seeks to determine whether the suspicious image was derived from the base image using an AI editing model, while attribution further identifies the specific editing model responsible. Existing methods for detecting and attributing AI-generated images are insufficient for this problem, as they focus on determining whether an image was AI-generated/edit…

[2025-10-01 Wed (UTC), 115 new articles found for cs.AI Artificial Intelligence]
toXiv_bot_toot

Link to download:
Judge Young’s 161-Page Love Letter to the Constitution Shreds Trump Admin, Defends First Amendment
https://michaelpopok.substack.com/p/judge-youngs-161-page-love-letter

ElasWave: An Elastic-Native System for Scalable Hybrid-Parallel Training
Xueze Kang, Guangyu Xiang, Yuxin Wang, Hao Zhang, Yuchu Fang, Yuhang Zhou, Zhenheng Tang, Youhui Lv, Eliran Maman, Mark Wasserman, Alon Zameret, Zhipeng Bian, Shushu Chen, Zhiyou Yu, Jin Wang, Xiaoyu Wu, Yang Zheng, Chen Tian, Xiaowen Chu
https://arxiv.org/abs/2510.00…

ElasWave: An Elastic-Native System for Scalable Hybrid-Parallel Training
Large-scale LLM pretraining today spans $10^{5}$--$10^{6}$ accelerators, making failures commonplace and elasticity no longer optional. We posit that an elastic-native training system must simultaneously ensure (i) Parameter Consistency, (ii) low Mean Time to Recovery (MTTR), (iii) high post-change Throughput, and (iv) Computation Consistency. This objective set not has never been jointly attained by prior work. To achieve these goals, we present ElasWave, which provides per-step fault toleranc…

Unsupervised Detection of Topological Phase Transitions with a Quantum Reservoir
Li Xin, Da Zhang, Zhang-Qi Yin
https://arxiv.org/abs/2509.25825 https://ar…

Unsupervised Detection of Topological Phase Transitions with a Quantum Reservoir
In quantum many-body systems, characterizing topological phase transitions typically requires complex many-body topological invariants, which are costly to compute and measure. Inspired by quantum reservoir computing, we propose an unsupervised quantum phase detection method based on a many-body localized evolution, enabling efficient identification of phase transitions in the extended SSH model. The evolved quantum states produce feature distributions under local measurements, which, after sim…

Ramsey numbers of long even cycles versus books
Qizhong Lin, Shixi Song
https://arxiv.org/abs/2509.26323 https://arxiv.org/pdf/2509.26323

Ramsey numbers of long even cycles versus books
For any positive integers $k$ and $n$, let $B_n^{(k)}$ be the book graph consisting of $n$ copies of the complete graph $K_{k+1}$ sharing a common $K_k$. Let $C_m$ be a cycle of length $m$. Prior work by Allen, Łuczak, Polcyn, and Zhang (2023) established the Ramsey number $R(C_{m},B_n^{(1)})$ for all sufficiently large even integer $m = Ω(n^{9/10})$. Recently, Hu, Lin, Łuczak, Ning, and Peng (2025) obtained the exact value of $R(C_{m},B_n^{(2)})$ under the same asymptotic conditions. A natu…

[2025-10-01 Wed (UTC), 16 new articles found for cs.CY Computers and Society]
toXiv_bot_toot

Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading
Nagur Shareef Shaik, Teja Krishna Cherukuri, Adnan Masood, Ehsan Adeli, Dong Hye Ye
https://arxiv.org/abs/2509.26146

Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading
Diabetic retinopathy grading is inherently ordinal and long-tailed, with minority stages being scarce, heterogeneous, and clinically critical to detect accurately. Conventional methods often rely on isotropic Gaussian priors and symmetric loss functions, misaligning latent representations with the task's asymmetric nature. We propose the Constrained Asymmetric Prior Wasserstein Autoencoder (CAP-WAE), a novel framework that addresses these challenges through three key innovations. Our approach e…

Strategic Fusion of Vision Language Models: Shapley-Credited Context-Aware Dawid-Skene for Multi-Label Tasks in Autonomous Driving
Yuxiang Feng, Keyang Zhang, Hassane Ouchouid, Ashwil Kaniamparambil, Ioannis Souflas, Panagiotis Angeloudis
https://arxiv.org/abs/2510.01126

Strategic Fusion of Vision Language Models: Shapley-Credited Context-Aware Dawid-Skene for Multi-Label Tasks in Autonomous Driving
Large vision-language models (VLMs) are increasingly used in autonomous-vehicle (AV) stacks, but hallucination limits their reliability in safety-critical pipelines. We present Shapley-credited Context-Aware Dawid-Skene with Agreement, a game-theoretic fusion method for multi-label understanding of ego-view dashcam video. It learns per-model, per-label, context-conditioned reliabilities from labelled history and, at inference, converts each model's report into an agreement-guardrailed log-likel…

Black-box Context-free Grammar Inference for Readable & Natural Grammars
Mohammad Rifat Arefin, Shanto Rahman, Christoph Csallner
https://arxiv.org/abs/2509.26616 https://…

Black-box Context-free Grammar Inference for Readable & Natural Grammars
Black-box context-free grammar inference is crucial for program analysis, reverse engineering, and security, yet existing tools such as Arvada, TreeVada, and Kedavra struggle with scalability, readability, and accuracy on large, complex languages. We present NatGI, a novel LLM-guided grammar inference framework that extends TreeVada's parse tree recovery with three key innovations: bracket-guided bubble exploration, LLM- driven bubble generation and non-terminal labeling, and hierarchical delta…

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Oskar Kviman, Kirill Tamogashev, Nicola Branchini, V\'ictor Elvira, Jens Lagergren, Nikolay Malkin
https://arxiv.org/abs/2510.01159

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajectories are available, but one has only snapshots of data taken at discrete time steps, the problem of modelling the dynamics, and thus inferring the underlying trajectories, can be solved by multi-marginal generalisations of flow matching algorithms. This paper proposes a novel flow matching method that overcomes the …

Universally Composable Termination Analysis of Tendermint
Zhixin Dong, Xian Xu, Yuhang Zeng, Mingchao Wan, Chunmiao Li
https://arxiv.org/abs/2510.01097 https://

Universally Composable Termination Analysis of Tendermint
Modern blockchain systems operating in adversarial environments require robust consensus protocols that guarantee both safety and termination under network delay attacks. Tendermint, a widely adopted consensus protocol in consortium blockchains, achieves high throughput and finality. However, previous analysis of the safety and termination has been done in a standalone fashion, with no consideration of the composition with other protocols interacting with it in a concurrent manner. Moreover, th…

Instant4D: 4D Gaussian Splatting in Minutes
Zhanpeng Luo, Haoxi Ran, Li Lu
https://arxiv.org/abs/2510.01119 https://arxiv.org/pdf/2510.01119

Instant4D: 4D Gaussian Splatting in Minutes
Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid prunin…

Towards Verified Code Reasoning by LLMs
Meghana Sistla, Gogul Balakrishnan, Pat Rondon, Jos\'e Cambronero, Michele Tufano, Satish Chandra
https://arxiv.org/abs/2509.26546 ht…

Towards Verified Code Reasoning by LLMs
While LLM-based agents are able to tackle a wide variety of code reasoning questions, the answers are not always correct. This prevents the agent from being useful in situations where high precision is desired: (1) helping a software engineer understand a new code base, (2) helping a software engineer during code review sessions, and (3) ensuring that the code generated by an automated code generation system meets certain requirements (e.g. fixes a bug, improves readability, implements a featur…

Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
Yesom Park, Shu Liu, Mo Zhou, Stanley Osher
https://arxiv.org/abs/2510.01153 https://arx…

Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
We present a novel framework for solving optimal transport (OT) problems based on the Hamilton--Jacobi (HJ) equation, whose viscosity solution uniquely characterizes the OT map. By leveraging the method of characteristics, we derive closed-form, bidirectional transport maps, thereby eliminating the need for numerical integration. The proposed method adopts a pure minimization framework: a single neural network is trained with a loss function derived from the method of characteristics of the HJ …

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[10/10]:
- Fiaingen: A financial time series generative method matching real-world data quality
Ro\v{z}anec, \v{Z}ezlin, Vasiliu, Mladeni\'c, Prodan, Roman

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
Gautier Evennou, Vivien Chappelier, Ewa Kijak
https://arxiv.org/abs/2510.00799 https://

Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors
Most image watermarking systems focus on robustness, capacity, and imperceptibility while treating the embedded payload as meaningless bits. This bit-centric view imposes a hard ceiling on capacity and prevents watermarks from carrying useful information. We propose LatentSeal, which reframes watermarking as semantic communication: a lightweight text autoencoder maps full-sentence messages into a compact 256-dimensional unit-norm latent vector, which is robustly embedded by a finetuned watermar…

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
Abdelrhman Werby, Dennis Rotondi, Fabio Scaparro, Kai O. Arras
https://arxiv.org/abs/2510.01049 https://…

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
In recent years, 3D scene graphs have emerged as a powerful world representation, offering both geometric accuracy and semantic richness. Combining 3D scene graphs with large language models enables robots to reason, plan, and navigate in complex human-centered environments. However, current approaches for constructing 3D scene graphs are semantically limited to a predefined set of relationships, and their serialization in large environments can easily exceed an LLM's context window. We introdu…

ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systems
Junsong Pu, Yichen Li, Zhuangbin Chen, Jinyang Liu, Zhihan Jiang, Jianjun Chen, Rui Shi, Zibin Zheng, Tieying Zhang
https://arxiv.org/abs/2509.26463

ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systems
Reliability management in cloud service systems is challenging due to the cascading effect of failures. Error wrapping, a practice prevalent in modern microservice development, enriches errors with context at each layer of the function call stack, constructing an error chain that describes a failure from its technical origin to its business impact. However, this also presents a significant traceability problem when recovering the complete error propagation path from the final log message back t…

Sample-Efficient Differentially Private Fine-Tuning via Gradient Matrix Denoising
Ali Dadsetan, Frank Rudzicz
https://arxiv.org/abs/2510.01137 https://arxi…

Sample-Efficient Differentially Private Fine-Tuning via Gradient Matrix Denoising
We address the challenge of sample efficiency in differentially private fine-tuning of large language models (LLMs) using DP-SGD. While DP-SGD provides strong privacy guarantees, the added noise significantly increases the entropy of gradient matrices, disrupting their low-rank structure and slowing optimization. We propose a post-processing algorithm that leverages random matrix theory to denoise gradients, restore low-rank structure, and improve alignment with the original signal. Applied to …

Generalized Parallel Scaling with Interdependent Generations
Harry Dong, David Brandfonbrener, Eryk Helenowski, Yun He, Mrinal Kumar, Han Fang, Yuejie Chi, Karthik Abinav Sankararaman
https://arxiv.org/abs/2510.01143

Generalized Parallel Scaling with Interdependent Generations
Parallel LLM inference scaling involves sampling a set of $N>1$ responses for a single input prompt. However, these $N$ parallel responses tend to be generated independently from each other, partitioning compute resources and leaving potentially useful information in one generation untapped by others. This is in contrast to response length scaling where past computation is used in all future steps. For higher quality responses and response sets, we propose Bridge to generate interdependent resp…

A Monoid Ring Approach to Color Visual Cryptography
Maximilian Reif, Jens Zumbr\"agel
https://arxiv.org/abs/2510.00763 https://arxiv.org/pdf/2510.0076…

A Monoid Ring Approach to Color Visual Cryptography
A visual cryptography scheme is a secret sharing scheme in which the secret information is an image and the shares are printed on transparencies, so that the secret image can be recovered by simply stacking the shares on top of each other. Such schemes do therefore not require any knowledge of cryptography tools to recover the secret, and they have widespread applications, for example, when sharing QR codes or medical images. In this work we deal with visual cryptography threshold schemes for c…

Authentic Discrete Diffusion Model
Xiao Li, Jiaqi Zhang, Shuxiang Zhang, Tianshui Chen, Liang Lin, Guangrun Wang
https://arxiv.org/abs/2510.01047 https://a…

Authentic Discrete Diffusion Model
We propose an Authentic Discrete Diffusion (ADD) framework that fundamentally redefines prior pseudo-discrete approaches by preserving core diffusion characteristics directly in the one-hot space through a suite of coordinated mechanisms. Unlike conventional "pseudo" discrete diffusion (PDD) methods, ADD reformulates the diffusion input by directly using float-encoded one-hot class data, without relying on diffusing in the continuous latent spaces or masking policies. At its core, a timestep-co…

EQ-Robin: Generating Multiple Minimal Unique-Cause MC/DC Test Suites
Robin Lee, Youngho Nam
https://arxiv.org/abs/2509.26458 https://arxiv.org/pdf/2509.264…

EQ-Robin: Generating Multiple Minimal Unique-Cause MC/DC Test Suites
Modified Condition/Decision Coverage (MC/DC), particularly its strict Unique-Cause form, is a cornerstone of safety-critical software verification. A recent algorithm, "Robin's Rule," introduced a deterministic method to construct the theoretical minimum of N+1 test cases for Singular Boolean Expressions (SBEs). However, this approach yields only a single test suite, introducing a critical risk: if a test case forming a required 'independence pair' is an illegal input forbidden by system constr…

TabINR: An Implicit Neural Representation Framework for Tabular Data Imputation
Vincent Ochs, Florentin Bieder, Sidaty el Hadramy, Paul Friedrich, Stephanie Taha-Mehlitz, Anas Taha, Philippe C. Cattin
https://arxiv.org/abs/2510.01136

TabINR: An Implicit Neural Representation Framework for Tabular Data Imputation
Tabular data builds the basis for a wide range of applications, yet real-world datasets are frequently incomplete due to collection errors, privacy restrictions, or sensor failures. As missing values degrade the performance or hinder the applicability of downstream models, and while simple imputing strategies tend to introduce bias or distort the underlying data distribution, we require imputers that provide high-quality imputations, are robust across dataset sizes and yield fast inference. We …

Apriel-1.5-15b-Thinker
Shruthan Radhakrishna, Aman Tiwari, Aanjaneya Shukla, Masoud Hashemi, Rishabh Maheshwary, Shiva Krishna Reddy Malay, Jash Mehta, Pulkit Pattnaik, Saloni Mittal, Khalil Slimi, Kelechi Ogueji, Akintunde Oladipo, Soham Parikh, Oluwanifemi Bamgbose, Toby Liang, Ahmed Masry, Khyati Mahajan, Sai Rajeswar Mudumba, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Torsten Scholak, Sagar Davasam, Srinivas Sunkara, Nicholas Chapados

Apriel-1.5-15b-Thinker
We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthet…

IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
Ahsan Farabi, Muhaiminul Rashid Shad, Israt Khandaker
https://arxiv.org/abs/2510.00572

IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
Intrusion Detection Systems (IDS) face persistent challenges due to evolving cyberattacks, high-dimensional traffic data, and severe class imbalance in benchmark datasets such as NSL-KDD. To address these issues, we propose IntrusionX, a hybrid deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction and Long Short-Term Memory (LSTM) networks for temporal modeling. The architecture is further optimized using the Squirrel Search Algorithm (SSA), e…

Secure and reversible face anonymization with diffusion models
Pol Labarbarie, Vincent Itier, William Puech
https://arxiv.org/abs/2510.01031 https://arxiv.…

Secure and reversible face anonymization with diffusion models
Face images processed by computer vision algorithms contain sensitive personal information that malicious actors can capture without consent. These privacy and security risks highlight the need for effective face anonymization methods. Current methods struggle to propose a good trade-off between a secure scheme with high-quality image generation and reversibility for later person authentication. Diffusion-based approaches produce high-quality anonymized images but lack the secret key mechanism …

Institutional Policy Pathways for Supporting Research Software: Global Trends and Local Practices
Michelle Barker, Jeremy Cohen, Pedro Hern\'andez Serrano, Daniel S. Katz, Kim Martin, Dan Rudmann, Hugh Shanahan
https://arxiv.org/abs/2509.26422

Institutional Policy Pathways for Supporting Research Software: Global Trends and Local Practices
As research software becomes increasingly central to modern science, research-performing organisations (RPOs) need to ensure that their investment in people, skills and infrastructure around research software produces sustainable and maintainable software that improves the research they perform, which in turn improves the overall institution and its reputation and funding, for example, by competing with peers who lack this approach. However, research institution management and recognition of re…

Prompt Curriculum Learning for Efficient LLM Post-Training
Zhaolin Gao, Joongwon Kim, Wen Sun, Thorsten Joachims, Sid Wang, Richard Yuanzhe Pang, Liang Tan
https://arxiv.org/abs/2510.01135

Prompt Curriculum Learning for Efficient LLM Post-Training
We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL remains sensitive to batching and prompt selection strategies, we first conduct a series of systematic experiments where we (1) determine the optimal training batch size that balances generation efficiency and gradient quality and (2) establish the importance of f…

Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
Evan Heus, Rick Bookstaber, Dhruv Sharma
https://arxiv.org/abs/2510.01115 https://

Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use struc…

Sentry: Authenticating Machine Learning Artifacts on the Fly
Andrew Gan, Zahra Ghodsi
https://arxiv.org/abs/2510.00554 https://arxiv.org/pdf/2510.00554

Sentry: Authenticating Machine Learning Artifacts on the Fly
Machine learning systems increasingly rely on open-source artifacts such as datasets and models that are created or hosted by other parties. The reliance on external datasets and pre-trained models exposes the system to supply chain attacks where an artifact can be poisoned before it is delivered to the end-user. Such attacks are possible due to the lack of any authenticity verification in existing machine learning systems. Incorporating cryptographic solutions such as hashing and signing can m…

Towards Adversarial Training under Hyperspectral Images
Weihua Zhang, Chengze Jiang, Jie Gui, Lu Dong
https://arxiv.org/abs/2510.01014 https://arxiv.org/pd…

Towards Adversarial Training under Hyperspectral Images
Recent studies have revealed that hyperspectral classification models based on deep learning are highly vulnerable to adversarial attacks, which pose significant security risks. Although several approaches have attempted to enhance adversarial robustness by modifying network architectures, these methods often rely on customized designs that limit scalability and fail to defend effectively against strong attacks. To address these challenges, we introduce adversarial training to the hyperspectral…

UniSage: A Unified and Post-Analysis-Aware Sampling for Microservices
Zhouruixing Zhu, Zhihan Jiang, Tianyi Yang, Pinjia He
https://arxiv.org/abs/2509.26336 https://

UniSage: A Unified and Post-Analysis-Aware Sampling for Microservices
Traces and logs are essential for observability and fault diagnosis in modern distributed systems. However, their ever-growing volume introduces substantial storage overhead and complicates troubleshooting. Existing approaches typically adopt a sample-before-analysis paradigm: even when guided by data heuristics, they inevitably discard failure-related information and hinder transparency in diagnosing system behavior. To address this, we introduce UniSage, the first unified framework to sample …

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
Ruiyi Wang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01132 https://arxiv.o…

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars -- environment, reward, and policy -- and empirically derive a recipe for training LLM agents in situate…

PRISM-Consult: A Panel-of-Experts Architecture for Clinician-Aligned Diagnosis
Lionel Levine, John Santerre, Alexander S. Young, T. Barry Levine, Francis Campion, Majid Sarrafzadeh
https://arxiv.org/abs/2510.01114

PRISM-Consult: A Panel-of-Experts Architecture for Clinician-Aligned Diagnosis
We present PRISM-Consult, a clinician-aligned panel-of-experts architecture that extends the compact PRISM sequence model into a routed family of domain specialists. Episodes are tokenized as structured clinical events; a light-weight router reads the first few tokens and dispatches to specialist models (Cardiac-Vascular, Pulmonary, Gastro-Oesophageal, Musculoskeletal, Psychogenic). Each specialist inherits PRISM's small transformer backbone and token template, enabling parameter efficiency and…

Calyx: Privacy-Preserving Multi-Token Optimistic-Rollup Protocol
Dominik Apel, Zeta Avarikioti, Matteo Maffei, Yuheng Wang
https://arxiv.org/abs/2510.00164 https://

Calyx: Privacy-Preserving Multi-Token Optimistic-Rollup Protocol
Rollup protocols have recently received significant attention as a promising class of Layer 2 (L2) scalability solutions. By utilizing the Layer 1 (L1) blockchain solely as a bulletin board for a summary of the executed transactions and state changes, rollups enable secure off-chain execution while avoiding the complexity of other L2 mechanisms. However, to ensure data availability, current rollup protocols require the plaintext of executed transactions to be published on-chain, resulting in in…

ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
Yuxiang Guo, Jiang Liu, Ze Wang, Hao Chen, Ximeng Sun, Yang Zhao, Jialian Wu, Xiaodong Yu, Zicheng Liu, Emad Barsoum
https://arxiv.org/abs/2510.01010

ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing approaches typically quantify the quality of a generated image using a single scalar, limiting their ability to provide comprehensive and interpretable feedback on image quality. To address this, we introduce ImageDoctor, a unified multi-aspect T2I model evaluation fr…

Hamster: A Large-Scale Study and Characterization of Developer-Written Tests
Rangeet Pan, Tyler Stennett, Raju Pavuluri, Nate Levin, Alessandro Orso, Saurabh Sinha
https://arxiv.org/abs/2509.26204

Hamster: A Large-Scale Study and Characterization of Developer-Written Tests
Automated test generation (ATG), which aims to reduce the cost of manual test suite development, has been investigated for decades and has produced countless techniques based on a variety of approaches: symbolic analysis, search-based, random and adaptive-random, learning-based, and, most recently, large-language-model-based approaches. However, despite this large body of research, there is still a gap in our understanding of the characteristics of developer-written tests and, consequently, in …

Optimizing Fairness in Production Planning: A Human-Centric Approach to Machine and Workforce Allocation
Alexander Nasuta, Alessandro Cisi, Sylwia Olbrych, Gustavo Vieira, Rui Fernandes, Lucas Paletta, Marlene Mayr, Rishyank Chevuri, Robert Woitsch, Hans Aoyang Zhou, Anas Abdelrazeq, Robert H. Schmitt
https://arxiv.org/abs/2510.01094

Optimizing Fairness in Production Planning: A Human-Centric Approach to Machine and Workforce Allocation
This work presents a two-layer, human-centric production planning framework designed to optimize both operational efficiency and workforce fairness in industrial manufacturing. The first layer formulates the Order-Line allocation as a Constraint Programming (CP) problem, generating high-utilization production schedules that respect machine capacities, processing times, and due dates. The second layer models Worker-Line allocation as a Markov Decision Process (MDP), integrating human factors suc…

POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad, Nick Rahimi
https://arxiv.org/abs/2510.01009

POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
Video Question Answering (VQA) with Large Vision Language Models (LVLMs) has gained significant traction in research ever since the Flamingo was introduced by Deepmind. Recent advancements in large context/long video question answering have allowed VQA tasks to have context window of 1500+ frames. However, this only leads to 50 seconds of video footage without losing any significant information. We introduce POVQA, a data-efficient pipeline that compresses each second of video into a single tem…

Understanding Collective Social Behavior in OSS Communities: A Co-editing Network Analysis of Activity Cascades
Lisi Qarkaxhija, Maximilian Carparo, Stefan Menzel, Bernhard Sendhoff, Ingo Scholtes
https://arxiv.org/abs/2509.26173

Understanding Collective Social Behavior in OSS Communities: A Co-editing Network Analysis of Activity Cascades
Understanding the collective social behavior of software developers is crucial to model and predict the long-term dynamics and sustainability of Open Source Software (OSS) communities. To this end, we analyze temporal activity patterns of developers, revealing an inherently ``bursty'' nature of commit contributions. To investigate the social mechanisms behind this phenomenon, we adopt a network-based modelling framework that captures developer interactions through co-editing networks. Our frame…

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Guobin Shen, Dongcheng Zhao, Haibo Tong, Jindong Li, Feifei Zhao, Yi Zeng
https://arxiv.org/abs/2510.01088

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already possess robust internal safety beliefs: they consistently produce high-confidence refusals to harmful requests while exhibiting high entropy when generating potentially dangerous content. This entropy gap reveals an untapped signal--models intrinsically "know" wh…

TextCAM: Explaining Class Activation Map with Text
Qiming Zhao, Xingjian Li, Xiaoyu Cao, Xiaolong Wu, Min Xu
https://arxiv.org/abs/2510.01004 https://arxiv…

TextCAM: Explaining Class Activation Map with Text
Deep neural networks (DNNs) have achieved remarkable success across domains but remain difficult to interpret, limiting their trustworthiness in high-stakes applications. This paper focuses on deep vision models, for which a dominant line of explainability methods are Class Activation Mapping (CAM) and its variants working by highlighting spatial regions that drive predictions. We figure out that CAM provides little semantic insight into what attributes underlie these activations. To address th…

A Multi-Language Object-Oriented Programming Benchmark for Large Language Models
Shuai Wang, Liang Ding, Li Shen, Yong Luo, Han Hu, Lefei Zhang, Fu Lin
https://arxiv.org/abs/2509.26111

A Multi-Language Object-Oriented Programming Benchmark for Large Language Models
Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three major imbalances: 85.7% focus on a single programming language; 94.3% target only function-level or statement-level tasks; and over 80% include fewer than ten test cases on average. To address these gaps, we propose MultiOOP, a multi-language object-oriented programming benchmark covering six popular languages (Pytho…

Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning
Elija Perrier
https://arxiv.org/abs/2510.01069 https://arxiv.org/pdf/2510.0106…

Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning
While Chain-of-Thought (CoT) prompting enhances the reasoning capabilities of large language models, the faithfulness of the generated rationales remains an open problem for model interpretability. We propose a novel theoretical lens for this problem grounded in the Curry-Howard correspondence, which posits a direct relationship between formal proofs and computer programs. Under this paradigm, a faithful reasoning trace is analogous to a well-typed program, where each intermediate step correspo…

SoftCFG: Uncertainty-guided Stable Guidance for Visual autoregressive Model
Dongli Xu, Aleksei Tiulpin, Matthew B. Blaschko
https://arxiv.org/abs/2510.00996 https://

SoftCFG: Uncertainty-guided Stable Guidance for Visual autoregressive Model
Autoregressive (AR) models have emerged as powerful tools for image generation by modeling images as sequences of discrete tokens. While Classifier-Free Guidance (CFG) has been adopted to improve conditional generation, its application in AR models faces two key issues: guidance diminishing, where the conditional-unconditional gap quickly vanishes as decoding progresses, and over-guidance, where strong conditions distort visual coherence. To address these challenges, we propose SoftCFG, an unce…

Agent-based code generation for the Gammapy framework
Dmitriy Kostunin, Vladimir Sotnikov, Sergo Golovachev, Abhay Mehta, Tim Lukas Holch, Elisa Jones
https://arxiv.org/abs/2509.26110

Agent-based code generation for the Gammapy framework
Software code generation using Large Language Models (LLMs) is one of the most successful applications of modern artificial intelligence. Foundational models are very effective for popular frameworks that benefit from documentation, examples, and strong community support. In contrast, specialized scientific libraries often lack these resources and may expose unstable APIs under active development, making it difficult for models trained on limited or outdated data. We address these issues for th…

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Akchunya Chanchal, David A. Kelly, Hana Chockler
https://arxiv.org/abs/2510.01038 https://…

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
Black-box explainability methods are popular tools for explaining the decisions of image classifiers. A major drawback of these tools is their reliance on mutants obtained by occluding parts of the input, leading to out-of-distribution images. This raises doubts about the quality of the explanations. Moreover, choosing an appropriate occlusion value often requires domain knowledge. In this paper we introduce a novel forward-pass paradigm Activation-Deactivation (AD), which removes the effects o…

Visual Self-Refinement for Autoregressive Models
Jiamian Wang, Ziqi Zhou, Chaithanya Kumar Mummadi, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Chen Qiu, Zhiqiang Tao
https://arxiv.org/abs/2510.00993 …

Visual Self-Refinement for Autoregressive Models
Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to suboptimal results. This work proposes a plug-and-play refinement module to enhance the complex spatial correspondence modeling within the generated visual sequence. This module operates as a post-pretraining step to jointly refine all generated tokens of autoregr…

Evaluating the impact of code smell refactoring on the energy consumption of Android applications
Hina Anwar, Dietmar Pfahl, Satish N. Srirama
https://arxiv.org/abs/2509.26031 h…

Evaluating the impact of code smell refactoring on the energy consumption of Android applications
Energy consumption of mobile apps is a domain that is receiving a lot of attention from researchers. Recent studies indicate that the energy consumption of mobile devices could be improved by improving the quality of mobile apps. Frequent refactoring is one way of achieving this goal. In this paper, we explore the performance and energy impact of several common code refactorings in Android apps. Experimental results indicate that some code smell refactorings positively impact the energy consump…

Uncovering the Computational Ingredients of Human-Like Representations in LLMs
Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee, Siddharth Suresh
https://arxiv.org/abs/2510.01030

Uncovering the Computational Ingredients of Human-Like Representations in LLMs
The ability to translate diverse patterns of inputs into structured patterns of behavior has been thought to rest on both humans' and machines' ability to learn robust representations of relevant concepts. The rapid advancement of transformer-based large language models (LLMs) has led to a diversity of computational ingredients -- architectures, fine tuning methods, and training datasets among others -- but it remains unclear which of these ingredients are most crucial for building models that …

A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
https://arxiv.org/abs/2510.00978

A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
Visually localizing an image, i.e., estimating its camera pose, requires building a scene representation that serves as a visual map. The representation we choose has direct consequences towards the practicability of our system. Even when starting from mapping images with known camera poses, state-of-the-art approaches still require hours of mapping time in the worst case, and several minutes in the best. This work raises the question whether we can achieve competitive accuracy much faster. We …

Using GPT to build a Project Management assistant for Jira environments
Joel Garcia-Escribano, Arkaitz Carbajo, Mikel Ega\~na Aranguren, Unai Lopez-Novoa
https://arxiv.org/abs/2509.26014

Using GPT to build a Project Management assistant for Jira environments
In the domain of Project Management, the sheer volume of data is a challenge that project managers continually have to deal with. Effectively steering projects from inception to completion requires handling of diverse information streams, including timelines, budgetary considerations, and task dependencies. To navigate this data-driven landscape with precision and agility, project managers must rely on efficient and sophisticated tools. These tools have become essential, as they enable project …

Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling
Federico Tiblias, Irina Bigoulaeva, Jingcheng Niu, Simone Balloccu, Iryna Gurevych
https://arxiv.org/abs/2510.01025

Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling
The linear representation hypothesis states that language models (LMs) encode concepts as directions in their latent space, forming organized, multidimensional manifolds. Prior efforts focus on discovering specific geometries for specific features, and thus lack generalization. We introduce Supervised Multi-Dimensional Scaling (SMDS), a model-agnostic method to automatically discover feature manifolds. We apply SMDS to temporal reasoning as a case study, finding that different features form var…

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
Siheng Wan, Zhengtao Yao, Zhengdao Li, Junhao Dong, Yanshu Li, Yikai Li, Linshan Li, Haoyan Xu, Yijiang Li, Zhikang Dong, Huacan Wang, Jifeng Shen
https://arxiv.org/abs/2510.00974

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified multimodal framework that encodes images and captions into discrete visual and textual tokens, processed by a joint-embedding predictive Transformer. To enhance fusion, we incorporate cross-attention after the feature predictor for conditional denoising while main…

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
Yilun Liu, Ziang Chen, Song Xu, Minggui He, Shimin Tao, Weibin Meng, Yuming Xie, Tao Han, Chunguang Zhao, Jingzhou Du, Daimeng Wei, Shenglin Zhang, Yongqian Sun
https://arxiv.org/abs/2509.25987

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
The growing complexity of log data in modern software systems has prompted the use of Large Language Models (LLMs) for automated log analysis. Current approaches typically rely on direct supervised fine-tuning (SFT) on log-label pairs. However, this exacerbates the domain discrepancy between general-purpose LLMs and specialized log data, causing overfitting. Furthermore, SFT's imbalanced loss computation often allows lengthy contexts to overwhelm critical, concise details in model answers, lead…

Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer
Saravanan Venkatachalam
https://arxiv.org/abs/2510.01006

Integrating AI and Ensemble Forecasting: Explainable Materials Planning with Scorecards and Trend Insights for a Large-Scale Manufacturer
This paper presents a practical architecture for after-sales demand forecasting and monitoring that unifies a revenue- and cluster-aware ensemble of statistical, machine-learning, and deep-learning models with a role-driven analytics layer for scorecards and trend diagnostics. The framework ingests exogenous signals (installed base, pricing, macro indicators, life cycle, seasonality) and treats COVID-19 as a distinct regime, producing country-part forecasts with calibrated intervals. A Pareto-a…

InfVSR: Breaking Length Limits of Generic Video Super-Resolution
Ziqing Zhang, Kai Liu, Zheng Chen, Xi Li, Yucong Chen, Bingnan Duan, Linghe Kong, Yulun Zhang
https://arxiv.org/abs/2510.00948

InfVSR: Breaking Length Limits of Generic Video Super-Resolution
Real-world videos often extend over thousands of frames. Existing video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of multi-step denoising for full-length sequences; and (2) poor scalability hindered by temporal decomposition that causes artifacts and discontinuities. To break these limits, we propose InfVSR, which novelly reformulates VSR as an autoregressive-one-step-diffusion paradigm. This…

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
Simin Chen, Yixin He, Suman Jana, Baishakhi Ray
https://arxiv.org/abs/2509.25894 https://…

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities
LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair (APR). APR agents automatically fetch GitHub issues and use backend LLMs to generate patches that fix the reported bugs. However, existing work primarily focuses on the functional correctness of APR-generated patches, whether they pass hidden or regression tests, while largely ignoring potential security risks. Given the openness of platforms like GitHub, where any user can raise issues an…

Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
Aueaphum Aueawatthanaphisut
https://arxiv.org/abs/2510.00976 https://

Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
Rare-disease diagnosis remains one of the most pressing challenges in digital health, hindered by extreme data scarcity, privacy concerns, and the limited resources of edge devices. This paper proposes the Adaptive Federated Few-Shot Rare-Disease Diagnosis (AFFR) framework, which integrates three pillars: (i) few-shot federated optimization with meta-learning to generalize from limited patient samples, (ii) energy-aware client scheduling to mitigate device dropouts and ensure balanced participa…

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
Zanwu Liu, Chao Yuan, Bo Li, Xiaowei Zhang, Guanglin Niu
https://arxiv.org/abs/2510.00936

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
In surveillance scenarios, varying camera distances cause significant differences among pedestrian image resolutions, making it hard to match low-resolution (LR) images with high-resolution (HR) counterparts, limiting the performance of Re-Identification (ReID) tasks. Most existing Cross-Resolution ReID (CR-ReID) methods rely on super-resolution (SR) or joint learning for feature compensation, which increases training and inference complexity and has reached a performance bottleneck in recent s…

LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Zhihan Jiang, Jinyang Liu, Yichen Li, Haiyu Huang, Xiao He, Tieying Zhang, Jianjun Chen, Yi Li, Rui Shi, Michael R. Lyu
https://arxiv.org/abs/2509.25874

LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems
Effective alert diagnosis is essential for ensuring the reliability of large-scale online service systems. However, on-call engineers are often burdened with manually inspecting massive volumes of logs to identify root causes. While various automated tools have been proposed, they struggle in practice due to alert-agnostic log scoping and the inability to organize complex data effectively for reasoning. To overcome these limitations, we introduce LogPilot, an intent-aware and scalable framework…

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Cong Yu, Valter Uotila, Shilong Deng, Qingyuan Wu, Tuo Shi, Songlin Jiang, Lei You, Bo Zhao
https://arxiv.org/abs/2510.00967

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic solution. However, the fundamental challenges remain unaddressed: (i) parameterized quantum gates require precise numerical values for optimal performance, which also depend on multiple aspects, including the number of quantum gates, their parameters, and the layout/depth of the…

Equivariant Splitting: Self-supervised learning from incomplete data
Victor Sechaud, J\'er\'emy Scanvic, Quentin Barth\'elemy, Patrice Abry, Juli\'an Tachella
https://arxiv.org/abs/2510.00929

Equivariant Splitting: Self-supervised learning from incomplete data
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equiva…

Are Classical Clone Detectors Good Enough For the AI Era?
Ajmain Inqiad Alam, Palash Roy, Farouq Al-omari, Chanchal Roy, Banani Roy, Kevin Schneider
https://arxiv.org/abs/2509.25754

Are Classical Clone Detectors Good Enough For the AI Era?
The increasing adoption of AI-generated code has reshaped modern software development, introducing syntactic and semantic variations in cloned code. Unlike traditional human-written clones, AI-generated clones exhibit systematic syntactic patterns and semantic differences learned from large-scale training data. This shift presents new challenges for classical code clone detection (CCD) tools, which have historically been validated primarily on human-authored codebases and optimized to detect sy…

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
Miha O\v{z}bot, Igor \v{S}krjanc, Vitomir \v{S}truc
https://arxiv.org/abs/2510.00960 https://

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
In the complex landscape of multivariate time series forecasting, achieving both accuracy and interpretability remains a significant challenge. This paper introduces the Fuzzy Transformer (Fuzzformer), a novel recurrent neural network architecture combined with multi-head self-attention and fuzzy inference systems to analyze multivariate stock market data and conduct long-term time series forecasting. The method leverages LSTM networks and temporal attention to condense multivariate data into i…

PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
Ali Shadman Yazdi, Annalisa Cappella, Benedetta Baldini, Riccardo Solazzo, Gianluca Tartaglia, Chiarella Sforza, Giuseppe Baselli
https://arxiv.org/abs/2510.00910

PAL-Net: A Point-Wise CNN with Patch-Attention for 3D Facial Landmark Localization
Manual annotation of anatomical landmarks on 3D facial scans is a time-consuming and expertise-dependent task, yet it remains critical for clinical assessments, morphometric analysis, and craniofacial research. While several deep learning methods have been proposed for facial landmark localization, most focus on pseudo-landmarks or require complex input representations, limiting their clinical applicability. This study presents a fully automated deep learning pipeline (PAL-Net) for localizing 5…

DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation
Esakkivel Esakkiraja, Denis Akhiyarov, Aditya Shanmugham, Chitra Ganapathy
https://arxiv.org/abs/2509.25716

DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation
Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code generation for auto-completion and agentic AI applications. We address the problem of API leaks in current code-to-code benchmark datasets by introducing a new dataset built from real-world ServiceNow Script Includes that capture the challenge of unclear API us…

Test-Time Search in Neural Graph Coarsening Procedures for the Capacitated Vehicle Routing Problem
Yoonju Sim, Hyeonah Kim, Changhyun Kwon
https://arxiv.org/abs/2510.00958 https…

Test-Time Search in Neural Graph Coarsening Procedures for the Capacitated Vehicle Routing Problem
The identification of valid inequalities, such as the rounded capacity inequalities (RCIs), is a key component of cutting plane methods for the Capacitated Vehicle Routing Problem (CVRP). While a deep learning-based separation method can learn to find high-quality cuts, our analysis reveals that the model produces fewer cuts than expected because it is insufficiently sensitive to generate a diverse set of generated subsets. This paper proposes an alternative: enhancing the performance of a trai…

Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
Yucheng Lu, Hubert Dariusz Zaj\k{a}c, Veronika Cheplygina, Amelia Jim\'enez-S\'anchez
https://arxiv.org/abs/2510.00902

Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
Transfer learning is crucial for medical imaging, yet the selection of source datasets - which can impact the generalizability of algorithms, and thus patient outcomes - often relies on researchers' intuition rather than systematic principles. This study investigates these decisions through a task-based survey with machine learning practitioners. Unlike prior work that benchmarks models and experimental setups, we take a human-centered HCI perspective on how practitioners select source datasets…

Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation
Fang Liu, Tianze Wang, Li Zhang, Zheyu Yang, Jing Jiang, Zian Sun
https://arxiv.org/abs/2509.25676

Explainable Fault Localization for Programming Assignments via LLM-Guided Annotation
Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization (FL) techniques have demonstrated promising results in identifying errors in programs. However, existing FL techniques face challenges when applied to educational contexts. Most approaches operate at the method level without explanatory feedback, resulting i…

On Discovering Algorithms for Adversarial Imitation Learning
Shashank Reddy Chirra, Jayden Teoh, Praveen Paruchuri, Pradeep Varakantham
https://arxiv.org/abs/2510.00922 https://…

On Discovering Algorithms for Adversarial Imitation Learning
Adversarial Imitation Learning (AIL) methods, while effective in settings with limited expert demonstrations, are often considered unstable. These approaches typically decompose into two components: Density Ratio (DR) estimation $\frac{ρ_E}{ρ_π}$, where a discriminator estimates the relative occupancy of state-action pairs under the policy versus the expert; and Reward Assignment (RA), where this ratio is transformed into a reward signal used to train the policy. While significant research h…

AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Roshan Kenia, Anfei Li, Rishabh Srivastava, Kaveri A. Thakoor
https://arxiv.org/abs/2510.00882

AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Multi-Task Consistency Fine-tuning for 3D Glaucoma Classification
Glaucoma is a progressive eye disease that leads to optic nerve damage, causing irreversible vision loss if left untreated. Optical coherence tomography (OCT) has become a crucial tool for glaucoma diagnosis, offering high-resolution 3D scans of the retina and optic nerve. However, the conventional practice of condensing information from 3D OCT volumes into 2D reports often results in the loss of key structural details. To address this, we propose a novel hybrid deep learning model that integra…

M&SCheck: Towards a Checklist to Support Software Engineering Newcomers to the Modeling and Simulation Area
Luiza Martins de Freitas Cintra, Philipp Zech, Mohamad Kassab, Eliomar Ara\'ujo Lima, Sofia Larissa da Costa Paiva, Valdemar Vicente Graciano Neto
https://arxiv.org/abs/2509.25625

M&SCheck: Towards a Checklist to Support Software Engineering Newcomers to the Modeling and Simulation Area
The advent of increasingly complex and dynamic ecosystems, such as digital twins (DT), smart cities and Industry 4.0 and 5.0, has made evident the need to include modeling and simulation (M&S) in the software development life cycle. Such disruptive systems include simulation models in their own architecture (such as DT) or require the use of simulation models to represent the high degree of movement and the multiplicity of interactions that occur between the involved systems. However, when soft…

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
Hyun-kyu Ko, Youbin Kim, Jihyeon Park, Dongheok Park, Gyeongjin Kang, Wonjun Cho, Hyung Yi, Eunbyung Park
https://arxiv.org/abs/2510.00862

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their quadratic complexity and limited scalability make them less suited for long sequences. Video super-resolution (VSR) methods have traditionally relied on recurrent architectures to propagate features across frames. However, such approaches suffer from well-known issue…

AGNOMIN - Architecture Agnostic Multi-Label Function Name Prediction
Yonatan Gizachew Achamyeleh, Tongtao Zhang, Joshua Hyunki Kim, Gabriel Garcia, Shih-Yuan Yu, Anton Kocheturov, Mohammad Abdullah Al Faruque
https://arxiv.org/abs/2509.25514

AGNOMIN - Architecture Agnostic Multi-Label Function Name Prediction
Function name prediction is crucial for understanding stripped binaries in software reverse engineering, a key step for \textbf{enabling subsequent vulnerability analysis and patching}. However, existing approaches often struggle with architecture-specific limitations, data scarcity, and diverse naming conventions. We present AGNOMIN, a novel architecture-agnostic approach for multi-label function name prediction in stripped binaries. AGNOMIN builds Feature-Enriched Hierarchical Graphs (FEHGs),…

Can World Models Benefit VLMs for World Dynamics?
Kevin Zhang, Kuangzhi Ge, Xiaowei Chi, Renrui Zhang, Shaojun Shi, Zhen Dong, Sirui Han, Shanghang Zhang
https://arxiv.org/abs/2510.00855

Can World Models Benefit VLMs for World Dynamics?
Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question: with the advent of strong video foundational models, might they supplant conventional vision encoder paradigms for general-purpose multimodal understanding? While recent studies have begun to explore the potential of world models on common vision tasks, these…

BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions
Yinghang Ma (Jack), Jiho Shin (Jack), Leuson Da Silva (Jack), Zhen Ming (Jack), Jiang, Song Wang, Foutse Khomh, Shin Hwei Tan
https://arxiv.org/abs/2509.25465

BloomAPR: A Bloom's Taxonomy-based Framework for Assessing the Capabilities of LLM-Powered APR Solutions
Recent advances in large language models (LLMs) have accelerated the development of AI-driven automated program repair (APR) solutions. However, these solutions are typically evaluated using static benchmarks such as Defects4J and SWE-bench, which suffer from two key limitations: (1) the risk of data contamination, potentially inflating evaluation results due to overlap with LLM training data, and (2) limited ability to assess the APR capabilities in dynamic and diverse contexts. In this paper,…

Feature Identification for Hierarchical Contrastive Learning
Julius Ott, Nastassia Vysotskaya, Huawei Sun, Lorenzo Servadei, Robert Wille
https://arxiv.org/abs/2510.00837 https:…

Feature Identification for Hierarchical Contrastive Learning
Hierarchical classification is a crucial task in many applications, where objects are organized into multiple levels of categories. However, conventional classification approaches often neglect inherent inter-class relationships at different hierarchy levels, thus missing important supervisory signals. Thus, we propose two novel hierarchical contrastive learning (HMLC) methods. The first, leverages a Gaussian Mixture Model (G-HMLC) and the second uses an attention mechanism to capture hierarchy…

PIPer: On-Device Environment Setup via Online Reinforcement Learning
Alexander Kovrigin, Aleksandra Eliseeva, Konstantin Grotov, Egor Bogomolov, Yaroslav Zharov
https://arxiv.org/abs/2509.25455

PIPer: On-Device Environment Setup via Online Reinforcement Learning
Environment setup-the process of configuring the system to work with a specific software project-represents a persistent challenge in Software Engineering (SE). Automated environment setup methods could assist developers by providing fully configured environments for arbitrary repositories without manual effort. This also helps SE researchers to scale execution-based benchmarks. However, recent studies reveal that even state-of-the-art Large Language Models (LLMs) achieve limited success in aut…

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
Xiangtao Kong, Rongyuan Wu, Shuaizheng Liu, Lingchen Sun, Lei Zhang
https://arxiv.org/abs/2510.00820

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
Most recent real-world image super-resolution (Real-ISR) methods employ pre-trained text-to-image (T2I) diffusion models to synthesize the high-quality image either from random Gaussian noise, which yields realistic results but is slow due to iterative denoising, or directly from the input low-quality image, which is efficient but at the price of lower output quality. These approaches train ControlNet or LoRA modules while keeping the pre-trained model fixed, which often introduces over-enhance…

A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
Johan Lin{\aa}ker, Cailean Osborne, Jennifer Ding, Ben Burtenshaw
https://arxiv.org/abs/2509.25397

A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
The proliferation of open large language models (LLMs) is fostering a vibrant ecosystem of research and innovation in artificial intelligence (AI). However, the methods of collaboration used to develop open LLMs both before and after their public release have not yet been comprehensively studied, limiting our understanding of how open LLM projects are initiated, organized, and governed as well as what opportunities there are to foster this ecosystem even further. We address this gap through an …

PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
Thomas Campagnolo, Ezio Malis, Philippe Martinet, Gaetan Bahl
https://arxiv.org/abs/2510.00818 https://…

PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
Understanding how natural language phrases correspond to specific regions in images is a key challenge in multimodal semantic segmentation. Recent advances in phrase grounding are largely limited to single-view images, neglecting the rich geometric cues available in stereo vision. For this, we introduce PhraseStereo, the first novel dataset that brings phrase-region segmentation to stereo image pairs. PhraseStereo builds upon the PhraseCut dataset by leveraging GenStereo to generate accurate ri…

Detecting and Fixing API Misuses of Data Science Libraries Using Large Language Models
Akalanka Galappaththi, Francisco Ribeiro, Sarah Nadi
https://arxiv.org/abs/2509.25378 http…

What You See is What You Ask: Evaluating Audio Descriptions
Divy Kala, Eshika Khandelwal, Makarand Tapaswi
https://arxiv.org/abs/2510.00808 https://arxiv.o…

What You See is What You Ask: Evaluating Audio Descriptions
Audio descriptions (ADs) narrate important visual details in movies, enabling Blind and Low Vision (BLV) users to understand narratives and appreciate visual details. Existing works in automatic AD generation mostly focus on few-second trimmed clips, and evaluate them by comparing against a single ground-truth reference AD. However, writing ADs is inherently subjective. Through alignment and analysis of two independent AD tracks for the same movies, we quantify the subjectivity in when and whet…

Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development
Yuxuan Wan, Tingshuo Liang, Jiakai Xu, Jingyu Xiao, Yintong Huo, Michael R. Lyu
https://arxiv.org/abs/2509.25297

Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development
Developing full-stack web applications is complex and time-intensive, demanding proficiency across diverse technologies and frameworks. Although recent advances in multimodal large language models (MLLMs) enable automated webpage generation from visual inputs, current solutions remain limited to front-end tasks and fail to deliver fully functional applications. In this work, we introduce TDDev, the first test-driven development (TDD)-enabled LLM-agent framework for end-to-end full-stack web app…

From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation
Fan Yang, Zhiyang Chen, Yousong Zhu, Xin Li, Jinqiao Wang
https://arxiv.org/abs/2510.00806

From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation
Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to predict coarse-grained motion trajectories that maintain consistency with real-world physics. Second, these trajectories guide video generation through attention-based mechanisms for fine-grained motion refinement. We build a trajectory prediction dataset ba…

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
Pratik Shah, Rajat Ghosh, Aryan Singhal, Debojyoti Dutta
https://arxiv.org/abs/2509.25257 https://

RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities, or natural language queries (for example, describing a task and retrieving the corresponding code…

Solar PV Installation Potential Assessment on Building Facades Based on Vision and Language Foundation Models
Ruyu Liu, Dongxu Zhuang, Jianhua Zhang, Arega Getaneh Abate, Per Sieverts Nielsen, Ben Wang, Xiufeng Liu
https://arxiv.org/abs/2510.00797

Solar PV Installation Potential Assessment on Building Facades Based on Vision and Language Foundation Models
Building facades represent a significant untapped resource for solar energy generation in dense urban environments, yet assessing their photovoltaic (PV) potential remains challenging due to complex geometries and semantic com ponents. This study introduces SF-SPA (Semantic Facade Solar-PV Assessment), an automated framework that transforms street-view photographs into quantitative PV deployment assessments. The approach combines com puter vision and artificial intelligence techniques to addres…

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Zehua Zhang, Ati Priya Bajaj, Divij Handa, Siyu Liu, Arvind S Raj, Hongkai Chen, Hulin Wang, Yibo Liu, Zion Leonahenahe Basque, Souradip Nath, Vishal Juneja, Nikhil Chapre, Yan Shoshitaishvili, Adam Doup\'e, Chitta Baral, Ruoyu Wang
https://arxiv.org/abs/2…

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on manually curated rules and workflows, which cannot adapt to OSS that requires customized configuration or environment setup. Recent attempts using Large Language Models (LLMs) used selective evaluation on a subset of highly rated OSS, a practice that underestimates the realistic challenges of OSS compilation. In pract…

MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts
Yifan Shen, Yangyang Shu, Hye-young Paik, Yulei Sui
https://arxiv.org/abs/2510.00796 ht…

MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts
Recent advances in text-to-image (T2I) models, especially diffusion-based architectures, have significantly improved the visual quality of generated images. However, these models continue to struggle with a critical limitation: maintaining semantic consistency when input prompts undergo minor linguistic variations. Despite being logically equivalent, such prompt pairs often yield misaligned or semantically inconsistent images, exposing a lack of robustness in reasoning and generalisation. To ad…

Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
Krishna Vamshi Bodla, Haizhao Yang
https://arxiv.org/abs/2509.25247 https://arxiv.…

Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
Since the introduction of Large Language Models (LLMs), they have been widely adopted for various tasks such as text summarization, question answering, speech-to-text translation, and more. In recent times, the use of LLMs for code generation has gained significant attention, with tools such as Cursor and Windsurf demonstrating the ability to analyze massive code repositories and recommend relevant changes. Big tech companies have also acknowledged the growing reliance on LLMs for code generati…

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
Haifei Zhang, Patrick Barry, Eduardo Brandao
https://arxiv.org/abs/2510.00773 https://

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept pred…

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun, Jacques Klein, Tegawende F. Bissyande
https://arxiv.org/abs/2509.25243

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it suffers from verbosity and inefficiency. Chain-of-Draft (CoD) prompting offers more concise reasoning, but the stochastic nature of LLMs produces varying solution quality, making optimal selection challenging. We propose \multicod, a reinforcement learning fram…

ZQBA: Zero Query Black-box Adversarial Attack
Joana C. Costa, Tiago Roxo, Hugo Proen\c{c}a, Pedro R. M. In\'acio
https://arxiv.org/abs/2510.00769 https://

ZQBA: Zero Query Black-box Adversarial Attack
Current black-box adversarial attacks either require multiple queries or diffusion models to produce adversarial samples that can impair the target model performance. However, these methods require training a surrogate loss or diffusion models to produce adversarial samples, which limits their applicability in real-world settings. Thus, we propose a Zero Query Black-box Adversarial (ZQBA) attack that exploits the representations of Deep Neural Networks (DNNs) to fool other networks. Instead of …

Multi-Objective Task-Aware Predictor for Image-Text Alignment
Eunki Kim, Na Min An, James Thorne, Hyunjung Shim
https://arxiv.org/abs/2510.00766 https://ar…

Multi-Objective Task-Aware Predictor for Image-Text Alignment
Evaluating image-text alignment while reflecting human preferences across multiple aspects is a significant issue for the development of reliable vision-language applications. It becomes especially crucial in real-world scenarios where multiple valid descriptions exist depending on contexts or user needs. However, research progress is hindered by the lack of comprehensive benchmarks and existing evaluation predictors lacking at least one of these key properties: (1) Alignment with human judgmen…