English
Related papers

Related papers: Self-Distillation Enables Continual Learning

200 papers

Audio-visual representation learning is crucial for advancing multimodal speech processing tasks, such as lipreading and audio-visual speech recognition. Recently, speech foundation models (SFMs) have shown remarkable generalization…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-11 Jing-Xuan Zhang , Genshun Wan , Jianqing Gao , Zhen-Hua Ling

Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Yang Zhou , Zhanhao He , Keyu Lu , Guanhong Wang , Gaoang Wang

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…

Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data selection methods suffer from severe domain specificity:…

Computation and Language · Computer Science 2026-02-02 Junyou Su , He Zhu , Xiao Luo , Liyu Zhang , Hong-Yu Zhou , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

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

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. A key challenge in LfD research is that users tend to provide…

Machine Learning · Computer Science 2022-02-16 Sravan Jayanthi , Letian Chen , Matthew Gombolay

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain…

Computation and Language · Computer Science 2023-05-30 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Sung Ju Hwang , Alexander Min

State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Jiho Jang , Seonhoon Kim , Kiyoon Yoo , Chaerin Kong , Jangho Kim , Nojun Kwak

While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Chi Hong , Jiyue Huang , Robert Birke , Dick Epema , Stefanie Roos , Lydia Y. Chen

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training strategies to…

Computer Vision and Pattern Recognition · Computer Science 2021-09-10 Tianhao Li , Limin Wang , Gangshan Wu

Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally -- they are, in fact,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Alex Gomez-Villa , Bartlomiej Twardowski , Lu Yu , Andrew D. Bagdanov , Joost van de Weijer

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and…

Machine Learning · Computer Science 2022-01-28 Beong-woo Kwak , Youngwook Kim , Yu Jin Kim , Seung-won Hwang , Jinyoung Yeo

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be…

Artificial Intelligence · Computer Science 2021-09-10 Anastasiia Usmanova , François Portet , Philippe Lalanda , German Vega

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is…

In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually relies on supervised fine-tuning or retrieval-augmented…

Computation and Language · Computer Science 2025-08-08 Kalle Kujanpää , Pekka Marttinen , Harri Valpola , Alexander Ilin