RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 112
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published Oct 2 • 9
Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features Paper • 2609.33463 • Published Sep 27 • 9
UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation Paper • 2611.16517 • Published 6 days ago • 15
Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement Paper • 2611.08318 • Published 13 days ago • 23