CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion ModelsResearchSep 30, 2026
The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent InterfaceResearchSep 30, 2026
MERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression AnalysisResearchSep 30, 2026
StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action TasksResearchSep 30, 2026
Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated ContentResearchSep 30, 2026