English
Related papers

Related papers: HINT-SD: Targeted Hindsight Self-Distillation for …

200 papers

Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…

Machine Learning · Computer Science 2025-09-19 Mohammad Saif Nazir , Chayan Banerjee

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Computation and Language · Computer Science 2025-02-28 Yudi Zhang , Lu Wang , Meng Fang , Yali Du , Chenghua Huang , Jun Wang , Qingwei Lin , Mykola Pechenizkiy , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

Machine Learning · Computer Science 2026-02-04 Mahyar Alinejad , Yue Wang , George Atia

While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…

Machine Learning · Computer Science 2024-05-07 Maryam Hashemzadeh , Elias Stengel-Eskin , Sarath Chandar , Marc-Alexandre Cote

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Machine Learning · Computer Science 2026-04-22 Linwei Dong , Ruoyu Guo , Ge Bai , Zehuan Yuan , Yawei Luo , Changqing Zou

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance…

Machine Learning · Computer Science 2026-03-20 Zhicong Lu , Zichuan Lin , Wei Jia , Changyuan Tian , Deheng Ye , Peiguang Li , Li Jin , Nayu Liu , Guangluan Xu , Wei Feng

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Computation and Language · Computer Science 2024-02-20 Zizhong Li , Haopeng Zhang , Jiawei Zhang

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Lu Qi , Jason Kuen , Jiuxiang Gu , Zhe Lin , Yi Wang , Yukang Chen , Yanwei Li , Jiaya Jia

The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO apply sequence-level rewards uniformly to all tokens,…

Artificial Intelligence · Computer Science 2026-05-19 Zhenlin Wei , Pu Jian , Yingzhuo Deng , Xiaohan Wang , Jiajun Chai , Zhexin Hu , Wei Lin , Shanbin Zhang , Guojun Yin

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Xuerui Zhang , Xuehao Wang , Zhan Zhuang , Linglan Zhao , Ziyue Li , Xinmin Zhang , Zhihuan Song , Yu Zhang

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Geon Yeong Park , Sang Wan Lee , Jong Chul Ye

On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher, providing dense token-level rewards without external…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Lei Huang , Xiang Cheng , Chenxiao Zhao , Jindong Li , Dongcheng Zhao , Xing Yu

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can…

In this paper, we propose the first self-distillation framework for general object detection, termed LGD (Label-Guided self-Distillation). Previous studies rely on a strong pretrained teacher to provide instructive knowledge that could be…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Peizhen Zhang , Zijian Kang , Tong Yang , Xiangyu Zhang , Nanning Zheng , Jian Sun

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Yuxi Ren , Xin Xia , Yanzuo Lu , Jiacheng Zhang , Jie Wu , Pan Xie , Xing Wang , Xuefeng Xiao

Knowledge distillation (KD) has been shown to be highly effective in guiding a student model with a larger teacher model and achieving practical benefits in improving the computational and memory efficiency for large language models (LLMs).…

Computation and Language · Computer Science 2024-06-06 Chen Jia

Although diffusion models have achieved strong results in decision-making tasks, their slow inference speed remains a key limitation. While consistency models offer a potential solution, existing applications to decision-making either…

Machine Learning · Computer Science 2026-02-09 Xintong Duan , Yutong He , Fahim Tajwar , Ruslan Salakhutdinov , J. Zico Kolter , Jeff Schneider

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between…

Machine Learning · Computer Science 2025-05-27 Chen Jia

Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in…

Machine Learning · Computer Science 2020-10-27 Hossein Mobahi , Mehrdad Farajtabar , Peter L. Bartlett