English
Related papers

Related papers: Self-distillation with Online Diffusion on Batch M…

200 papers

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks.…

Artificial Intelligence · Computer Science 2026-05-25 Aristotelis Lazaridis , Dylan Bates , Aman Sharma , Brian King , Vincent Lu , Jack FitzGerald

Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains challenging because self-generated trajectories are…

Computation and Language · Computer Science 2026-05-22 Yiqiao Jin , Yiyang Wang , Lucheng Fu , Yijia Xiao , Yinyi Luo , Haoxin Liu , B. Aditya Prakash , Josiah Hester , Jindong Wang , Srijan Kumar

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Computation and Language · Computer Science 2025-04-29 Wenda Xu , Rujun Han , Zifeng Wang , Long T. Le , Dhruv Madeka , Lei Li , William Yang Wang , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser…

Machine Learning · Computer Science 2026-05-14 Weichen Yu , Xiaomin Li , Yizhou Zhao , Xiaoze Liu , Ruowang Zhang , Haixin Wang , Yinyi Luo , Chen Henry Wu , Gaurav Mittal , Matt Fredrikson , Yu Hu

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Xucong Wang , Pengchao Han , Lei Guo

Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Luozhou Wang , Shuai Yang , Shu Liu , Ying-cong Chen

Modern machine learning models heavily rely on large datasets that often include sensitive and private information, raising serious privacy concerns. Differentially private (DP) data generation offers a solution by creating synthetic…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Runkai Zheng , Vishnu Asutosh Dasu , Yinong Oliver Wang , Haohan Wang , Fernando De la Torre

RGB-D salient object detection (SOD) demonstrates its superiority on detecting in complex environments due to the additional depth information introduced in the data. Inevitably, an independent stream is introduced to extract features from…

Computer Vision and Pattern Recognition · Computer Science 2022-06-03 Guangyu Ren , Yinxiao Yu , Hengyan Liu , Tania Stathaki

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Yuan Zhang , Chenyi Li , Guoqing Ma , Jiajun Zha , Yuanming Yang , Bo Wang , Wei Tang , Wenbo Li , Haoyang Huang , Nan Duan

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Machine Learning · Computer Science 2020-08-24 Rohan Anil , Gabriel Pereyra , Alexandre Passos , Robert Ormandi , George E. Dahl , Geoffrey E. Hinton

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Computation and Language · Computer Science 2025-04-08 Yixing Li , Yuxian Gu , Li Dong , Dequan Wang , Yu Cheng , Furu Wei

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Xinhao Zhong , Shuoyang Sun , Xulin Gu , Zhaoyang Xu , Yaowei Wang , Min Zhang , Bin Chen

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Rui Xie , Chen Zhao , Kai Zhang , Zhenyu Zhang , Jun Zhou , Jian Yang , Ying Tai

The complex and dynamic real-world clinical environment demands reliable deep learning (DL) systems. Out-of-distribution (OOD) detection plays a critical role in enhancing the reliability and generalizability of DL models when encountering…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Jiangbei Yue , Darren Treanor , Venkataraman Subramanian , Sharib Ali

Diffusion models offer superior generation quality at the expense of extensive sampling steps. Distillation methods, with Distribution Matching Distillation (DMD) as a popular example, can mitigate this issue, but performance degradation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Xu Wang , Zexian Li , Litong Gong , Tiezheng Ge , Zhijie Deng

In speech enhancement, knowledge distillation (KD) compresses models by transferring a high-capacity teacher's knowledge to a compact student. However, conventional KD methods train the student to mimic the teacher's output entirely, which…

Sound · Computer Science 2026-01-27 Dohwan Kim , Jung-Woo Choi

Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Jieren Deng , Xin Zhou , Hao Tian , Zhihong Pan , Derek Aguiar

Diffusion Probability Models (DPMs) have made impressive advancements in various machine learning domains. However, achieving high-quality synthetic samples typically involves performing a large number of sampling steps, which impedes the…

Machine Learning · Computer Science 2024-12-16 Shitong Shao , Xu Dai , Lujun Li , Huanran Chen , Yang Hu , Shouyi Yin

Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Liang Yao , Fan Liu , Chuanyi Zhang , Zhiquan Ou , Ting Wu
‹ Prev 1 8 9 10 Next ›