On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics Paper • 2609.35259 • Published 14 days ago • 202
Eliciting Numerical Predictive Distributions of LLMs Without Autoregression Paper • 2603.02913 • Published Mar 3 • 1
Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models Paper • 2511.21338 • Published Nov 26, 2025 • 2