English
Related papers

Related papers: TCOD: Exploring Temporal Curriculum in On-Policy D…

200 papers

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Computation and Language · Computer Science 2026-05-12 Haoyang Zhou , Li Kong , Shijie Ren , Xiting Wang , Shuang Liang , Guowei Wang , Zhenxuan Pan

On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to…

Machine Learning · Computer Science 2026-05-11 Junfeng Fang , Zhepei Hong , Mao Zheng , Mingyang Song , Gengsheng Li , Houcheng Jiang , Dan Zhang , Haiyun Guo , Xiang Wang , Tat-Seng Chua

On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-level signals along its own trajectories. This framework typically uses reverse KL divergence,…

Machine Learning · Computer Science 2026-05-25 Woogyeol Jin , Taywon Min , Yongjin Yang , Swanand Ravindra Kadhe , Yi Zhou , Dennis Wei , Nathalie Baracaldo , Kimin Lee

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…

Machine Learning · Computer Science 2026-04-22 Weixiao Zhan , Yongcheng Jing , Leszek Rutkowski , Dacheng Tao

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

On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's…

Artificial Intelligence · Computer Science 2026-05-14 Junlong Ke , Zichen Wen , Weijia Li , Conghui He , Linfeng Zhang

On-policy distillation (OPD) is widely used for LLM post-training. When pushed with a reward-extrapolation coefficient lambda > 1, the student can lift past the teacher in domain, but past a threshold lambda* the same step violates the…

Machine Learning · Computer Science 2026-05-12 Xin Li , Hao Jiang , Annan Wang , Yichi Zhang , Chau Yuen

Knowledge distillation (KD) has emerged as a promising technique for addressing the computational challenges associated with deploying large-scale recommender systems. KD transfers the knowledge of a massive teacher system to a compact…

Information Retrieval · Computer Science 2024-06-27 Gyuseok Lee , SeongKu Kang , Wonbin Kweon , Hwanjo Yu

Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high…

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Computation and Language · Computer Science 2026-03-17 Minsang Kim , Seung Jun Baek

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

Knowledge Distillation (KD) aims to transfer a more capable teacher model's knowledge to a lighter student model in order to improve the efficiency of the model, making it faster and more deployable. However, the student model's…

Machine Learning · Computer Science 2024-03-19 Eugene Ku

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Computation and Language · Computer Science 2025-04-29 Wenda Xu , Rujun Han , Zifeng Wang , Long T. Le , Dhruv Madeka , Lei Li , William Yang Wang , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…

Machine Learning · Computer Science 2026-01-30 RuiQi Liu , Boyu Diao , Libo Huang , Zijia An , Hangda Liu , Zhulin An , Yongjun Xu

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

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

Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zhen Fang , Wenxuan Huang , Yu Zeng , Yiming Zhao , Shuang Chen , Kaituo Feng , Yunlong Lin , Lin Chen , Zehui Chen , Shaosheng Cao , Feng Zhao

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

Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Jianhua Zhang , Yi Gao , Ruyu Liu , Xu Cheng , Houxiang Zhang , Shengyong Chen

Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data converge to suboptimal joint behaviours because they cannot…