PAPER·2 days agoProgress Reward Modeling for Robotic Learning: A Comprehensive SurveyHugging Face Papers
PAPER·2 days agoDriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style IdentificationHugging Face Papers
PAPER·2 days agoStateAct: Program State, before Pixels, for Long-Horizon Computer-Use AgentsHugging Face Papers
PAPER·2 days agoOmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMsHugging Face Papers
PAPER·2 days agoInteractive Training 2: Auditable Control Plane for Live Model TrainingHugging Face Papers
PAPER·2 days agoO-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and ReasoningHugging Face Papers
PAPER·2 days agoSkill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving SkillsHugging Face Papers
