GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 93
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 43
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published Sep 30 • 50