English
Related papers

Related papers: Proximal Policy Distillation

200 papers

We aim to identify how different components in the KD pipeline affect the resulting performance and how much the optimal KD pipeline varies across different datasets/tasks, such as the data augmentation policy, the loss function, and the…

Computation and Language · Computer Science 2021-09-24 Haoyu He , Xingjian Shi , Jonas Mueller , Zha Sheng , Mu Li , George Karypis

Aligning small language models (SLMs) with human values typically involves distilling preference knowledge from large language models (LLMs). However, existing distillation methods model preference knowledge in teacher LLMs by comparing…

Computation and Language · Computer Science 2025-02-21 Yanggan Gu , Junzhuo Li , Sirui Huang , Xin Zou , Zhenghua Li , Xuming Hu

Thompson sampling (TS) has emerged as a robust technique for contextual bandit problems. However, TS requires posterior inference and optimization for action generation, prohibiting its use in many online platforms where latency and ease of…

Machine Learning · Computer Science 2024-07-23 Hongseok Namkoong , Samuel Daulton , Eytan Bakshy

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

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

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Yang Chen , Shuai Fu , 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

Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Chaomin Shen , Yaomin Huang , Haokun Zhu , Jinsong Fan , Guixu Zhang

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Weilun Feng , Chuanguang Yang , Zhulin An , Libo Huang , Boyu Diao , Fei Wang , Yongjun Xu

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Zhizhong Li , Avinash Ravichandran , Charless Fowlkes , Marzia Polito , Rahul Bhotika , Stefano Soatto

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

The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2019-10-11 Jiao Xie , Shaohui Lin , Yichen Zhang , Linkai Luo

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,…

Knowledge Distillation (KD) is a fundamental technique for compressing large language models (LLMs) into compact, efficient student models. However, existing white-box KD methods mainly focus on balancing ground truth and student-generated…

Computation and Language · Computer Science 2025-08-11 Lingyuan Liu , Mengxiang Zhang

With numerous medical tasks, the performance of deep models has recently experienced considerable improvements. These models are often adept learners. Yet, their intricate architectural design and high computational complexity make…

Image and Video Processing · Electrical Eng. & Systems 2023-03-17 Eddardaa Ben Loussaief , Hatem Rashwan , Mohammed Ayad , Mohammed Zakaria Hassan , Domenec Puig

Knowledge Distillation (KD), which transfers the knowledge of a well-trained large model (teacher) to a small model (student), has become an important area of research for practical deployment of recommender systems. Recently, Relaxed…

Information Retrieval · Computer Science 2024-05-16 Youngjune Lee , Kee-Eung Kim

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Machine Learning · Computer Science 2025-12-30 Amirhossein Tighkhorshid , Zahra Dehghanian , Gholamali Aminian , Chengchun Shi , Hamid R. Rabiee

With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt ChatGPT to generate…

Computation and Language · Computer Science 2024-01-29 Hailin Chen , Amrita Saha , Steven Hoi , Shafiq Joty

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

Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the…

Machine Learning · Computer Science 2020-02-04 Zhang-Wei Hong , Prabhat Nagarajan , Guilherme Maeda

Despite the success of Deep Learning (DL), the deployment of modern DL models requiring large computational power poses a significant problem for resource-constrained systems. This necessitates building compact networks that reduce…

Machine Learning · Computer Science 2020-06-24 Akshay Kulkarni , Navid Panchi , Sharath Chandra Raparthy , Shital Chiddarwar