GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 92
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published about 1 month ago • 42
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published Sep 30 • 50