Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published 1 day ago • 40
QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation Paper • 2608.29253 • Published 12 days ago • 14
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published 14 days ago • 150
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning Paper • 2607.29211 • Published Jul 31 • 14
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus Paper • 2608.12149 • Published 29 days ago • 30
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss Paper • 2608.11205 • Published 30 days ago • 27