4 papers · 1 filter
Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning
Yuanteng Chen, Zhilei Liu, Peisong Wang +7
Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reasoning subs…
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
Yao Shu, Chenxing Wei, Hongbin Lin +2
Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal, but it keeps rollout generation, verifier scoring, and refere…
Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling
Yiran Guo, Zhongjian Qiao, Yingqi Xie +5
Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast n…
HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models
Zhinan Xie, Peisong Wang, Shuang Qiu +1
Speculative decoding has proven effective for accelerating inference in Large Language Models (LLMs), yet its extension to Vision-Language Models (VLMs) remains limited by the comp…