English
Related papers

Related papers: KL for a KL: On-Policy Distillation with Control V…

200 papers

Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-training methods have made progress in long-context scaling, they either rely on high-quality…

Computation and Language · Computer Science 2026-04-21 Xinsen Zhang , Zhenkai Ding , Tianjun Pan , Run Yang , Chun Kang , Xue Xiong , Jingnan Gu

On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when this guidance spans the full response, all-token KL spends…

Artificial Intelligence · Computer Science 2026-05-12 Jiaxuan Wang , Xuan Ouyang , Zhiyu Chen , Yulan Hu , Zheng Pan , Xin Li , Lan-Zhe Guo

RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR…

Machine Learning · Computer Science 2026-05-01 Naibin Gu , Chenxu Yang , Qingyi Si , Chuanyu Qin , Dingyu Yao , Peng Fu , Zheng Lin , Weiping Wang , Nan Duan , Jiaqi Wang

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Dengyang Jiang , Xin Jin , Dongyang Liu , Zanyi Wang , Mingzhe Zheng , Ruoyi Du , Xiangpeng Yang , Qilong Wu , Zhen Li , Peng Gao , Harry Yang , Steven Hoi

Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised…

Machine Learning · Computer Science 2026-05-27 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor W. Tsang , Yang You

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

Computation and Language · Computer Science 2026-04-17 Shiwan Zhao , Zhihu Wang , Xuyang Zhao , Jiaming Zhou , Caiyue Xu , Chenfei Liu , Liting Zhang , Yuhang Jia , Yanzhe Zhang , Hualong Yu , Zichen Xu , Qicheng Li , Yong Qin

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements…

Machine Learning · Computer Science 2026-05-15 Zhengxi Lu , Zhiyuan Yao , Zhuowen Han , Zi-Han Wang , Jinyang Wu , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Computation and Language · Computer Science 2024-10-22 Yuhang Zhou , Jing Zhu , Paiheng Xu , Xiaoyu Liu , Xiyao Wang , Danai Koutra , Wei Ai , Furong Huang

Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advantage to every token, diluting the signal at pivotal reasoning…

Machine Learning · Computer Science 2026-05-25 Yu Li , Rui Miao , Tian Lan , Zhengling Qi

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

Machine Learning · Computer Science 2026-02-17 Emiliano Penaloza , Dheeraj Vattikonda , Nicolas Gontier , Alexandre Lacoste , Laurent Charlin , Massimo Caccia

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or…

Machine Learning · Computer Science 2026-05-22 Dong Nie

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Machine Learning · Computer Science 2026-05-29 Yan Chen , Taojie Zhu , Meng Zhang , Xin Chen , Jiaqi Huang , Dongyang Xu , Yizhi Wang

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…

Machine Learning · Computer Science 2026-05-28 Zehao Liu , Yuanpu Cao , Jinghui Chen , Vasant G. Honavar

On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two…

Computation and Language · Computer Science 2026-05-22 Jie Sun , Mao Zheng , Mingyang Song , Qiyong Zhong , Yilin Cheng , Bichuan Feng , Pengfei Liu , Junfeng Fang , Xiang Wang

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang

Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and…

Computation and Language · Computer Science 2024-09-23 Jun Rao , Xuebo Liu , Zepeng Lin , Liang Ding , Jing Li , Dacheng Tao , Min Zhang

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-31 Di Cao , Dongjie Fu , Hai Yu , Siqi Zheng , Xu Tan , Tao Jin

Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive signals encoded in intermediate representations. In this paper,…

Machine Learning · Computer Science 2026-05-29 Xinyu Liu , Darryl Cherian Jacob , Yang Zhou , Jindong Wang , Pan He

Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the…

Computation and Language · Computer Science 2026-05-29 Zizhuo Lin , Quanling Liu , Jinsheng Quan , Chao Zhang , Yifan Zhu , Xing Shi , Jingtao Xu , Zhihui Li , Yawei Luo