4 papers
Self-Supervised On-Policy Distillation for Reasoning Language Models
Zhiquan Tan, Yinrong Hong
GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We show that a mixed group con…
PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners
Zhiquan Tan, Yinrong Hong
Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement lea…
A Theoretical Lens for RL-Tuned Language Models via Energy-Based Models
Zhiquan Tan, Yinrong Hong
Large language models (LLMs) trained via KL-regularized reinforcement learning demonstrate strong instruction following, self-correction, and reasoning abilities. Yet their theoret…
Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models
Yinrong Hong, Zhiquan Tan, Kai Hu
Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges a…