Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
Yangyang Zhong, Yanmei Gu, Zhengqing Zang +14
Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent current models truly realize these ca…
cs.CL2026
Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning
Bodong Du, Xuanqi Huang, Xiaomeng Li
Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are…