English
Related papers

Related papers: Bidirectional Distillation: A Mixed-Play Framework…

200 papers

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Computation and Language · Computer Science 2024-12-19 Tianyu Peng , Jiajun Zhang

Learning style refers to a type of training mechanism adopted by an individual to gain new knowledge. As suggested by the VARK model, humans have different learning preferences, like Visual (V), Auditory (A), Read/Write (R), and Kinesthetic…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Usma Niyaz , Abhishek Singh Sambyal , Deepti R. Bathula

Planning is a data efficient decision-making strategy where an agent selects candidate actions by exploring possible future states. To simulate future states when there is a high-dimensional action space, the knowledge of one's decision…

Artificial Intelligence · Computer Science 2024-03-25 Jaesung Yoo , Fernanda de la Torre , Guangyu Robert Yang

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Machine Learning · Computer Science 2026-02-24 David Li , Nikita Gushchin , Dmitry Abulkhanov , Eric Moulines , Ivan Oseledets , Maxim Panov , Alexander Korotin

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Chuanguang Yang , Xinqiang Yu , Han Yang , Zhulin An , Chengqing Yu , Libo Huang , Yongjun Xu

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…

Machine Learning · Computer Science 2026-05-08 Miao Rang , Zhenni Bi , Hang Zhou , Kai Han , Xuechun Wang , An Xiao , Xinghao Chen , Yunhe Wang , Hanting Chen

In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. In this paper, we propose an alternative approach whereby agents communicate through an…

Artificial Intelligence · Computer Science 2022-05-26 Dianbo Liu , Vedant Shah , Oussama Boussif , Cristian Meo , Anirudh Goyal , Tianmin Shu , Michael Mozer , Nicolas Heess , Yoshua Bengio

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has shown remarkable success in solving complex non-cooperative…

Artificial Intelligence · Computer Science 2025-10-21 Ruize Zhang , Zelai Xu , Chengdong Ma , Chao Yu , Wei-Wei Tu , Wenhao Tang , Shiyu Huang , Deheng Ye , Wenbo Ding , Yaodong Yang , Yu Wang

The focus of this paper is a Bayesian framework for solving a class of problems termed multi-agent inverse reinforcement learning (MIRL). Compared to the well-known inverse reinforcement learning (IRL) problem, MIRL is formalized in the…

Computer Science and Game Theory · Computer Science 2019-07-31 Xiaomin Lin , Peter A. Beling , Randy Cogill

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…

Computation and Language · Computer Science 2026-05-13 Xueqi Cheng , Xugui Zhou , Tyler Derr , Yushun Dong

In recent years, the rapid development of deep neural networks has brought increased attention to the security and robustness of these models. While existing adversarial attack algorithms have demonstrated success in improving adversarial…

Machine Learning · Computer Science 2025-02-25 Wenyuan Wu , Zheng Liu , Yong Chen , Chao Su , Dezhong Peng , Xu Wang

Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a systematic collaboration in which rapidly growing computing…

Machine Learning · Computer Science 2023-12-27 Shiye Lei , Dacheng Tao

In recent years, with the progress of deep learning technologies, crowd counting has been rapidly developed. In this work, we propose a simple yet effective crowd counting framework that is able to achieve the state-of-the-art performance…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Yue Gu , Wenxi Liu

Modeling the nonlinear dynamics of neuronal populations represents a key pursuit in computational neuroscience. Recent research has increasingly focused on jointly modeling neural activity and behavior to unravel their interconnections.…

Neural and Evolutionary Computing · Computer Science 2025-02-07 Zhengrui Guo , Fangxu Zhou , Wei Wu , Qichen Sun , Lishuang Feng , Jinzhuo Wang , Hao Chen

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but…

Artificial Intelligence · Computer Science 2025-07-30 Jonathan Light , Min Cai , Weiqin Chen , Guanzhi Wang , Xiusi Chen , Wei Cheng , Yisong Yue , Ziniu Hu

Knowledge distillation is a technique for improving the performance of a simple "student" model by replacing its one-hot training labels with a distribution over labels obtained from a complex "teacher" model. While this simple approach has…

Machine Learning · Computer Science 2020-05-22 Aditya Krishna Menon , Ankit Singh Rawat , Sashank J. Reddi , Seungyeon Kim , Sanjiv Kumar

Recent advances in offline Reinforcement Learning (RL) have proven that effective policy learning can benefit from imposing conservative constraints on pre-collected datasets. However, such static datasets often exhibit distribution bias,…

Machine Learning · Computer Science 2026-05-15 Yunpeng Qing , Yixiao Chi , Shuo Chen , Shunyu Liu , Kexuan Zhou , Sixu Lin , Litao Liu , Changqing Zou

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-08 Peng Zhou , Long Mai , Jianming Zhang , Ning Xu , Zuxuan Wu , Larry S. Davis

In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with…