10 posts published in the last hour
- 05:32Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses
- 05:32OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
- 05:31Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization
- 05:31One-Step Text Generation by Seq-Drifting
- 05:31Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing
- 05:02Neural networks are more modular than single neurons suggest
- 05:02Towards Defining, Measuring, and Leveraging Creativity in AI Applications
- 05:02EvoBelief: Falsifiable World Models for Self-Improving LLM Agents
- 05:02VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
- 05:02Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems