UCB is teaming with the Myasthenia Gravis Foundation of America and Factor Meals to provide premade meals to 250 families affected by myasthenia gravis, a chronic disease that can cause muscle weakness, fatigue and swallowing problems that make mealtimes especially difficult.
A digital cognitive behavioral therapy program culturally adapted for Spanish-speaking individuals with alcohol use disorder: a stage 1 randomized clinical trial
BackgroundDigital formats are an important tool for making evidence-based therapies for alcohol use, such as cognitive behavioral therapy (CBT), more broadly available, yet only a small percentage are available in Spanish and none with evidence from effectiveness studies with Spanish-speaking individuals. This study evaluated the feasibility and efficacy of adding a culturally-adapted, web-based CBT program […]
Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy
arXiv:2604.17182v1 Announce Type: cross Abstract: In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt — for example, in best-of-N sampling or multi-candidate code completion. These requests can share KV caches through a common prefix, yet the extent to which their Mixture-of-Experts (MoE) expert routing overlaps, and how this […]
HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
arXiv:2604.16499v1 Announce Type: cross Abstract: Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are available. Nevertheless, existing methods either […]
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
arXiv:2511.05993v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, leading to premature convergence to suboptimal local minima and hindering further performance improvement. Although various approaches have been […]
Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
arXiv:2604.18005v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the solution space remains unclear. We present a systematic empirical study of diversity in MAS-based ideation across three bottom-up levels: […]
Demystifying the unreasonable effectiveness of online alignment methods
arXiv:2604.17207v1 Announce Type: cross Abstract: Iterative alignment methods based on purely greedy updates are remarkably effective in practice, yet existing theoretical guarantees of (O(log T)) KL-regularized regret can seem pessimistic relative to their empirical performance. In this paper, we argue that this mismatch arises from the regret criterion itself: KL-regularized regret conflates the statistical cost […]
Scaling Test-Time Compute for Agentic Coding
arXiv:2604.16529v1 Announce Type: cross Abstract: Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken […]
Persona-Based Requirements Engineering for Explainable Multi-Agent Educational Systems: A Scenario Simulator for Clinical Reasoning Training
arXiv:2604.17186v1 Announce Type: cross Abstract: As Artificial Intelligence (AI) and Agentic AI become increasingly integrated across sectors such as education and healthcare, it is critical to ensure that Multi-Agent Education System (MAES) is explainable from the early stages of requirements engineering (RE) within the AI software development lifecycle. Explainability is essential to build trust, promote […]
Expert-Annotated Embryo Image Dataset with Natural Language Descriptions for Evidence-Based Patient Communication in IVF
arXiv:2604.16528v1 Announce Type: cross Abstract: Embryo selection is one of multiple crucial steps in in-vitro fertilization, commonly based on morphological assessment by clinical embryologists. Although artificial intelligence methods have demonstrated their potential to support embryo selection by automated embryo ranking or grading methods, the overall impact of AI-based solutions is still limited. This is mainly […]
LoReC: Rethinking Large Language Models for Graph Data Analysis
arXiv:2604.17897v1 Announce Type: cross Abstract: The advent of Large Language Models (LLMs) has fundamentally reshaped the way we interact with graphs, giving rise to a new paradigm called GraphLLM. As revealed in recent studies, graph learning can benefit from LLMs. However, we observe limited benefits when we directly utilize LLMs to make predictions for graph-related […]
CAMP: Cumulative Agentic Masking and Pruning for Privacy Protection in Multi-Turn LLM Conversations
arXiv:2604.16521v1 Announce Type: cross Abstract: The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally Identifiable Information (PII) masking operate on a per-turn basis, scanning each user message in isolation and replacing detected entities […]