Simplifying and Improving On-Policy Distillation for Few-Step Diffusion Paper • 2610.18472 • Published 4 days ago • 26
UNITAS: A 3D-Native World Action Model for Embodied Manipulation Paper • 2610.12099 • Published 9 days ago • 6
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 9 days ago • 249
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 9 days ago • 156
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability Paper • 2610.08448 • Published 11 days ago • 213
Hiding Tool Latency in On-Device Cascaded Voice Agent through Speculative Execution Paper • 2610.07641 • Published 11 days ago • 15
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory Paper • 2610.02521 • Published 16 days ago • 61