English
Related papers

Related papers: SOD: Step-wise On-policy Distillation for Small La…

200 papers

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Artificial Intelligence · Computer Science 2026-05-12 Han Yang , Mingyan Wu , Bailan He , Zeyu Cao , Sikuan Yan , Kevin Qinghong Lin , Zifeng Ding

Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and…

Software Engineering · Computer Science 2025-05-21 Yujia Chen , Yang Ye , Zhongqi Li , Yuchi Ma , Cuiyun Gao

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher model should be used,…

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Computation and Language · Computer Science 2025-10-10 Yuanjie Lyu , Chengyu Wang , Jun Huang , Tong Xu

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level…

Computation and Language · Computer Science 2026-05-22 Yuchen Cai , Ding Cao , Liang Lin , Chunxi Luo , Xin Xu , Kai Yang , Weijie Liu , Saiyong Yang , Tianxiang Zhao , Guangzhong Sun , Guiquan Liu , Junfeng Fang

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

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Qianhao Yuan , Jie Lou , Xing Yu , Hongyu Lin , Le Sun , Xianpei Han , Yaojie Lu

Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…

Machine Learning · Computer Science 2026-03-31 Shuozhi Yuan , Jinqing Wang , Zihao Liu , Miaomiao Yuan , Haoran Peng , Jin Zhao , Bingwen Wang , Haoyi Wang

Context distillation enables language models to internalize in-context knowledge into their parameters. In our work, we propose On-Policy Context Distillation (OPCD), a framework that bridges on-policy distillation with context distillation…

Computation and Language · Computer Science 2026-03-24 Tianzhu Ye , Li Dong , Xun Wu , Shaohan Huang , Furu Wei

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Sound · Computer Science 2023-09-18 Rayan Daod Nathoo , Mikolaj Kegler , Marko Stamenovic

Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools during long-form reasoning, such as search engines and code interpreters, to solve tasks beyond the capabilities of internal…

Artificial Intelligence · Computer Science 2025-06-03 Hongru Wang , Cheng Qian , Wanjun Zhong , Xiusi Chen , Jiahao Qiu , Shijue Huang , Bowen Jin , Mengdi Wang , Kam-Fai Wong , Heng Ji

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

On-Policy Self-Distillation (OPSD) has recently emerged as an alternative to Reinforcement Learning with Verifiable Rewards (RLVR), promising higher accuracy and shorter responses through token-level credit assignment from a self-teacher…

Artificial Intelligence · Computer Science 2026-05-08 Jaehoon Kim , Dongha Lee

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces…

Machine Learning · Computer Science 2026-05-26 Changyu Chen , Xiting Wang , Rui Yan

Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These approaches either train a language model from scratch or…

Computation and Language · Computer Science 2023-06-05 Qianhui Wu , Huiqiang Jiang , Haonan Yin , Börje F. Karlsson , Chin-Yew Lin

Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions. Existing online policy distillation (OPD) provides denser…

Artificial Intelligence · Computer Science 2026-05-27 Yanfei Zhang , Xu Lin , Chenglin Wu

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate…

Machine Learning · Computer Science 2026-05-28 Kun Liang , Chenming Tang , Clive Bai , Weijie Liu , Saiyong Yang , Yunfang Wu

On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rollouts with a teacher model. However, we observe ``Off-policy Teacher Decay'' problem in…

Machine Learning · Computer Science 2026-05-27 Zhou Ziheng , Jiaqi Li , Huacong Tang , Ying Nian Wu , Demetri Terzopoulos