FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation Paper • 2609.38839 • Published Sep 30 • 45
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 41
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published Oct 5 • 64
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching Paper • 2610.12421 • Published Oct 8 • 9
EvoOntology: A Self-Evolving Ontology Layer for Data Agents Paper • 2609.15779 • Published Sep 14 • 97