English
Related papers

Related papers: Rubric-based On-policy Distillation

200 papers

Offline imitation learning enables learning a policy solely from a set of expert demonstrations, without any environment interaction. To alleviate the issue of distribution shift arising due to the small amount of expert data, recent works…

Machine Learning · Computer Science 2025-05-23 Udita Ghosh , Dripta S. Raychaudhuri , Jiachen Li , Konstantinos Karydis , Amit K. Roy-Chowdhury

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Xiang Gu , Liming Lu , Xu Zheng , Anan Du , Yongbin Zhou , Shuchao Pang

Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose…

Information Retrieval · Computer Science 2026-05-14 Teng Chen , Sheng Xu , Feixiang Guo , Xiaoyu Wang , Qingqing Gu , Hongyan Li , Luo Ji

The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require…

Robotics · Computer Science 2024-10-22 Sihao Wu , Jiaxu Liu , Xiangyu Yin , Guangliang Cheng , Xingyu Zhao , Meng Fang , Xinping Yi , Xiaowei Huang

In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jiayan Li , Jun Li , Zhourui Zhang , Jianhua Xu

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

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

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

The rapid advancement in point cloud processing technologies has significantly increased the demand for efficient and compact models that achieve high-accuracy classification. Knowledge distillation has emerged as a potent model compression…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Qiang Zheng , Chao Zhang , Jian Sun

Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capability for autonomous GUI agents. Recent reinforcement learning methods (e.g., GRPO) have…

Artificial Intelligence · Computer Science 2026-05-12 Yan Zhang , Daiqing Wu , Huawen Shen , Can Ma , Yu Zhou

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric…

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

Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to…

Machine Learning · Computer Science 2017-06-02 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Bernhard Schölkopf , Sergey Levine

Rubrics provide a flexible way to train LLMs on open-ended long-form answers where verifiable rewards are not applicable and human preferences provide coarse signals. Prior work shows that reinforcement learning with rubric-based rewards…

Computation and Language · Computer Science 2025-10-13 MohammadHossein Rezaei , Robert Vacareanu , Zihao Wang , Clinton Wang , Bing Liu , Yunzhong He , Afra Feyza Akyürek

We propose a novel way to train ranking models, such as recommender systems, that are both effective and efficient. Knowledge distillation (KD) was shown to be successful in image recognition to achieve both effectiveness and efficiency. We…

Machine Learning · Computer Science 2018-09-21 Jiaxi Tang , Ke Wang

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…

Machine Learning · Computer Science 2026-02-12 Linxuan Xia , Xiaolong Yang , Yongyuan Chen , Enyue Zhao , Deng Cai , Yasheng Wang , Boxi Wu

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

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

Reinforcement Learning (RL) is known for its strong decision-making capabilities and has been widely applied in various real-world scenarios. However, with the increasing availability of offline datasets and the lack of well-designed online…

Machine Learning · Computer Science 2025-09-03 Hanping Zhang , Yuhong Guo