ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation Paper • 2609.39306 • Published 10 days ago • 33
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation Paper • 2610.02179 • Published 9 days ago • 20
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs Paper • 2610.01595 • Published 9 days ago • 6
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Paper • 2609.20511 • Published 23 days ago • 115
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models Paper • 2609.09143 • Published Sep 8 • 29
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation Paper • 2609.05588 • Published Sep 4 • 57