Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
Chenlu Ye, Xuanchang Zhang, Yifan Hao +6
Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribut…
cs.LG2026
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Siyan Zhao, Zhihui Xie, Mengchen Liu +4
Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this appro…
cs.LG2025
Inpainting-Guided Policy Optimization for Diffusion Large Language Models
Siyan Zhao, Mengchen Liu, Jing Huang +8
Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation ca…