Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs Paper • 2605.07447 • Published 5 days ago • 3
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs Paper • 2604.16659 • Published 26 days ago • 1
ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models Paper • 2604.08064 • Published Apr 9 • 8
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 324
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published Apr 9 • 289
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 627
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published Apr 9 • 100
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models Paper • 2603.22782 • Published Mar 24 • 20
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 311