Less from More: Reinforcing Sparse Video Reasoning from Dense References Paper • 2610.10893 • Published 8 days ago • 9
Continually Post-training Small Models via Synthetic Self-distillation Paper • 2610.13113 • Published 6 days ago • 45
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale Paper • 2610.08430 • Published 9 days ago • 27
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation Paper • 2610.07969 • Published 9 days ago • 22
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Paper • 2609.32607 • Published 19 days ago • 135
Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published 18 days ago • 38