arXiv:2603.17631v1 Announce Type: cross Abstract: The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and stochasticity inherent in both algorithmic learning and environmental dynamics. To manage this complexity, we introduce a rigorous benchmarking framework by […]
Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
arXiv:2602.10489v2 Announce Type: replace-cross Abstract: Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing methods attempt to reduce distributional shifts by aligning manually selected graph elements (e.g., node attributes or structural statistics), which typically require manually designed graph filters to extract […]
NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation
arXiv:2603.15352v2 Announce Type: replace-cross Abstract: While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To bridge this gap, we propose NV-Bench, the first benchmark grounded in a functional taxonomy that treats NVs as communicative acts rather than acoustic artifacts. NV-Bench comprises 1,651 multi-lingual, in-the-wild utterances […]
Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
arXiv:2603.17673v1 Announce Type: cross Abstract: LLM agents are increasingly relevant to research domains such as vulnerability discovery. Yet, the strongest systems remain closed and cloud-only, making them resource-intensive, difficult to reproduce, and unsuitable for work involving proprietary code or sensitive data. Consequently, there is an urgent need for small, local models that can perform security […]
rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks
arXiv:2603.17628v1 Announce Type: cross Abstract: Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to maximum likelihood estimation under a multinomial model. While statistically efficient under ideal conditions, this approach is highly vulnerable to contaminated […]
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
arXiv:2603.17812v1 Announce Type: cross Abstract: Recent video diffusion models achieve high-quality generation through recurrent frame processing where each frame generation depends on previous frames. However, this recurrent mechanism means that training such models in the pixel domain incurs prohibitive memory costs, as activations accumulate across the entire video sequence. This fundamental limitation also makes fine-tuning […]
“I’m Not Reading All of That”: Understanding Software Engineers’ Level of Cognitive Engagement with Agentic Coding Assistants
arXiv:2603.14225v2 Announce Type: replace-cross Abstract: Over-reliance on AI systems can undermine users’ critical thinking and promote complacency, a risk intensified by the emergence of agentic AI systems that operate with minimal human involvement. In software engineering, agentic coding assistants (ACAs) are rapidly becoming embedded in everyday development workflows. Since software engineers (SEs) create systems deployed […]
VideoAtlas: Navigating Long-Form Video in Logarithmic Compute
arXiv:2603.17948v1 Announce Type: cross Abstract: Extending language models to video introduces two challenges: representation, where existing methods rely on lossy approximations, and long-context, where caption- or agent-based pipelines collapse video into text and lose visual fidelity. To overcome this, we introduce textbfVideoAtlas, a task-agnostic environment to represent video as a hierarchical grid that is simultaneously […]
An optimal control approach to nonlinear wave speed selection in reaction-diffusion equations
arXiv:2603.17601v1 Announce Type: cross Abstract: Travelling wave solutions of reaction-diffusion equations are widely used to model the spatial spread of populations and other phenomena in biology and physics. In this article, we reinterpret the classical variational principle approach through an optimal control formulation, in order to obtain a lower bound on the invasion speed of […]
SAATT Nav: a Socially Aware Autonomous Transparent Transportation Navigation Framework for Wheelchairs
arXiv:2603.13698v2 Announce Type: replace-cross Abstract: While powered wheelchairs reduce physical fatigue as opposed to manual wheelchairs for individuals with mobility impairment, they demand high cognitive workload due to information processing, decision making and motor coordination. Current autonomous systems lack social awareness in navigation and transparency in decision-making, leading to decreased perceived safety and trust from […]
Theoretical Foundations of delta-margin Majority Voting
arXiv:2111.06390v4 Announce Type: replace-cross Abstract: In high-stakes ML applications such as fraud detection, medical diagnostics, and content moderation, practitioners rely on consensus-based approaches to control prediction quality. A particularly valuable technique — deltadelta delta-margin majority voting — collects votes sequentially until one label exceeds alternatives by a threshold deltadelta delta, offering stronger confidence than simple […]
A Contextual Help Browser Extension to Assist Digital Illiterate Internet Users
arXiv:2603.17592v1 Announce Type: cross Abstract: This paper describes the design, implementation, and evaluation of a browser extension that provides contextual help to users who hover over technological acronyms and abbreviations on web pages. The extension combines a curated technical dictionary with OpenAI’s large language model (LLM) to deliver on-demand definitions through lightweight tooltip overlays. A […]