arXiv:2605.14513v1 Announce Type: cross Abstract: Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive because it accelerates pretrained models without retraining, yet existing online top-$p$ sparse attention still spends non-negligible cost on mask prediction and […]
Conditional Attribute Estimation with Autoregressive Sequence Models
arXiv:2605.14004v1 Announce Type: new Abstract: Generative models are often trained with a next-token prediction objective, yet many downstream applications require the ability to estimate or control sequence-level properties. Next-token prediction can lead to overfitting of local patterns during training, underfitting of global structure, and requires significant downstream modifications or expensive sampling to guide or predict […]
Streaming Speech-to-Text Translation with a SpeechLLM
arXiv:2605.14766v1 Announce Type: cross Abstract: Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to reduce cascaded errors. But existing SpeechLLM systems are slow since they do not work in a […]
Do Language Models Align with Brains? Prediction Scores Are Not Enough
arXiv:2605.14025v1 Announce Type: new Abstract: Brain-language model comparisons often interpret neural prediction scores as evidence that model representations capture brain-relevant language computation. We asked whether language models align with brains, and whether prediction scores are enough to support that claim, using L-PACT, a source-audited framework that evaluates predictive, relational, mechanism-stripping, and reliability-bounded evidence. Across primary […]
Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
arXiv:2605.14897v1 Announce Type: cross Abstract: Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components […]
Spectral Analysis of Fake News Propagation
arXiv:2605.13861v1 Announce Type: cross Abstract: The propagation structure of fake news has been shown to be an important cue for detecting it; yet, existing propagation-based fake news detection methods have mainly relied on ad hoc topological features, and a unified view of cascade patterns is still lacking. To address this, we study news propagation from […]
Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents
arXiv:2605.14033v1 Announce Type: new Abstract: Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing representational framework remains transportable into a new regime, or whether its language has become locally-to-globally obstructed and must be extended. This paper develops a finite sheaf-theoretic framework for […]
Large Language Models for Web Accessibility: A Systematic Literature Review
arXiv:2605.13873v1 Announce Type: cross Abstract: Web accessibility aims to ensure that web content and services are usable by people with diverse abilities. In recent years, Large Language Models (LLMs) have been increasingly explored to support accessibility-related tasks on the web, such as content generation, issue detection, and remediation. However, little is known about the characteristics […]
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
arXiv:2605.15030v1 Announce Type: cross Abstract: Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard models still suffer from limited generalization to unseen domains and attack patterns, high false positive rates […]
A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study
arXiv:2605.13905v1 Announce Type: cross Abstract: Drug development and pharmacovigilance are frequently bottlenecked by legacy clinical reporting pipelines. These monolithic systems encode regulatory-grade logic but resist AI integration by producing opaque output with no machine-readable intermediate layer. Existing modernization approaches force a choice between full rewrites and incremental refactoring that preserves structural barriers. We present a […]
From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
arXiv:2605.14034v1 Announce Type: new Abstract: Wide applications of LLM-based agents require strong alignment with human social values. However, current works still exhibit deficiencies in self-cognition and dilemma decision, as well as self-emotions. To remedy this, we propose a novel value-based framework that employs GraphRAG to convert principles into value-based instructions and steer the agent to […]
A Regret Perspective on Online Multiple Testing
arXiv:2605.13916v1 Announce Type: cross Abstract: Online Multiple Testing (OMT), a fundamental pillar of sequential statistical inference, traditionally evaluates the False Discovery Rate (FDR) and statistical power in isolation, obscuring the highly asymmetric costs of false positives and false negatives in modern automated pipelines. To unify this evaluation, we introduce $textitWeighted Regret$. Under this metric, we […]