Researchers propose trace-based on-policy distillation (TOPD), a teacher-supervised framework that transfers reasoning ability to a diffusion large language model (dLLM) without reward estimation. TOP…
Researchers propose Trajectory-Aware Commit Gating (TACG), a training-free decoder for diffusion language models that uses trajectory-aware signals to decide when to commit tokens, improving accuracy …
Researchers introduced SEVRA, a serving-layer controller that decides when a frozen reasoning model should verify its answer instead of thinking longer, finding that selective verification improves ac…
Researchers propose SuperThoughts, a method that compresses pairs of consecutive Chain-of-Thought tokens into single latent representations and decodes two tokens per step, doubling inference throughp…
Researchers have developed Discrete Tilt Matching (DTM), a likelihood-free method for fine-tuning masked diffusion large language models using reinforcement learning. The approach recasts fine-tuning …