English
Related papers

Related papers: Stable Distillation and High-Dimensional Hypothesi…

200 papers

Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated outputs (e.g., correctness filtering, execution feedback, and…

Computation and Language · Computer Science 2026-05-22 Guangya Hao , Yitong Shang , Yunbo Long , Zhuokai Zhao , Hanxue Liang

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

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Nikita Starodubcev , Ilya Drobyshevskiy , Denis Kuznedelev , Artem Babenko , Dmitry Baranchuk

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

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which…

Machine Learning · Computer Science 2024-10-15 Nicolas Zilberstein , Morteza Mardani , Santiago Segarra

Self-distillation (SD), a technique where a model improves itself using its own predictions, has attracted attention as a simple yet powerful approach in machine learning. Despite its widespread use, the mechanisms underlying its…

Machine Learning · Statistics 2025-11-20 Kaito Takanami , Takashi Takahashi , Ayaka Sakata

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 He Liu , Yikai Wang , Huaping Liu , Fuchun Sun , Anbang Yao

We present the first provable method for identifying symmetric linear dynamical systems (LDS) with accuracy guarantees that are independent of the systems' state dimension or effective memory. Our approach builds upon recent work that…

Machine Learning · Computer Science 2025-05-26 Devan Shah , Shlomo Fortgang , Sofiia Druchyna , Elad Hazan

Dataset distillation aims to compress information from a large-scale original dataset to a new compact dataset while striving to preserve the utmost degree of the original data informational essence. Previous studies have predominantly…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Muxin Zhou , Zeyuan Yin , Shitong Shao , Zhiqiang Shen

The extraction of nonstationary signals from blind and semi-blind multivariate observations is a recurrent problem. Numerous algorithms have been developed for this problem, which are based on the exact or approximate joint diagonalization…

Signal Processing · Electrical Eng. & Systems 2021-08-27 Reza Sameni , Christian Jutten

Self-distillation (SD) is the process of first training a \enquote{teacher} model and then using its predictions to train a \enquote{student} model with the \textit{same} architecture. Specifically, the student's objective function is…

Machine Learning · Computer Science 2023-02-01 Rudrajit Das , Sujay Sanghavi

Histopathology can help clinicians make accurate diagnoses, determine disease prognosis, and plan appropriate treatment strategies. As deep learning techniques prove successful in the medical domain, the primary challenges become limited…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Zhe Li , Bernhard Kainz

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…

Computation and Language · Computer Science 2026-03-24 Edward Phillips , Sean Wu , Fredrik K. Gustafsson , Boyan Gao , David A. Clifton

Persistent homology is a vital tool for topological data analysis. Previous work has developed some statistical estimators for characteristics of collections of persistence diagrams. However, tools that provide statistical inference for…

Applications · Statistics 2016-02-23 Andrew Robinson , Katharine Turner

Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…

Machine Learning · Computer Science 2026-05-28 Ye Su , Hezhe Qiao , Wei Huang , Lin Chen

Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Shaobo Wang , Yantai Yang , Qilong Wang , Kaixin Li , Linfeng Zhang , Junchi Yan

We propose a new testing procedure of heteroskedasticity in high-dimensional linear regression, where the number of covariates can be larger than the sample size. Our testing procedure is based on residuals of the Lasso. We demonstrate that…

Statistics Theory · Mathematics 2022-11-01 Akira Shinkyu

Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current parameterization methods achieve enhanced performance under extremely high compression ratio by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Xinhao Zhong , Hao Fang , Bin Chen , Xulin Gu , Meikang Qiu , Shuhan Qi , Shu-Tao Xia

Supervised training of deep neural networks for classification typically relies on hard targets, which promote overconfidence and can limit calibration, generalization, and robustness. Self-distillation methods aim to mitigate this by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Anton Adelöw , Matteo Gamba , Atsuto Maki

Recent deep metric learning (DML) methods typically leverage solely class labels to keep positive samples far away from negative ones. However, this type of method normally ignores the crucial knowledge hidden in the data (e.g., intra-class…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Zelong Zeng , Fan Yang , Hong Liu , Shin'ichi Satoh