English
Related papers

Related papers: Distillation Scaling Laws

200 papers

The extra trust brought by the model interpretation has made it an indispensable part of machine learning systems. But to explain a distilled model's prediction, one may either work with the student model itself, or turn to its teacher…

Machine Learning · Computer Science 2020-05-26 Jinchao Huang , Guofu Li , Zhicong Yan , Fucai Luo , Shenghong Li

Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Chenglin Yang , Lingxi Xie , Chi Su , Alan L. Yuille

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

Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper…

Machine Learning · Computer Science 2025-05-28 Jing Xu , Jiazheng Li , Jingzhao Zhang

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Mobarakol Islam , Lalithkumar Seenivasan , S. P. Sharan , V. K. Viekash , Bhavesh Gupta , Ben Glocker , Hongliang Ren

In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing the size of the…

Machine Learning · Computer Science 2020-04-20 Hideki Oki , Motoshi Abe , Junichi Miyao , Takio Kurita

Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Yuanyang Yin , Yaqi Zhao , Mingwu Zheng , Ke Lin , Jiarong Ou , Rui Chen , Victor Shea-Jay Huang , Jiahao Wang , Xin Tao , Pengfei Wan , Di Zhang , Baoqun Yin , Wentao Zhang , Kun Gai

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainly focus on…

Computation and Language · Computer Science 2026-04-20 Yao Chen , Jiawei Sheng , Wenyuan Zhang , Tingwen Liu

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…

Machine Learning · Computer Science 2025-05-16 Tiancong Cheng , Ying Zhang , Yuxuan Liang , Roger Zimmermann , Zhiwen Yu , Bin Guo

The goal of model distillation is to faithfully transfer teacher model knowledge to a model which is faster, more generalizable, more interpretable, or possesses other desirable characteristics. Human-readability is an important and…

In the past decade, there has been substantial progress at training increasingly deep neural networks. Recent advances within the teacher--student training paradigm have established that information about past training updates show promise…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Liang Jiang , Zujie Wen , Zhongping Liang , Yafang Wang , Gerard de Melo , Zhe Li , Liangzhuang Ma , Jiaxing Zhang , Xiaolong Li , Yuan Qi

Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a…

Information Theory · Computer Science 2026-05-18 Bingying Li , Haiyun He

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…

Machine Learning · Computer Science 2026-04-22 Weixiao Zhan , Yongcheng Jing , Leszek Rutkowski , Dacheng Tao

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

Machine Learning · Computer Science 2022-11-03 Cody Blakeney , Jessica Zosa Forde , Jonathan Frankle , Ziliang Zong , Matthew L. Leavitt

Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inference-time decoding cost. We observe that, when solving the same…

Artificial Intelligence · Computer Science 2026-05-12 Han Yang , Mingyan Wu , Bailan He , Zeyu Cao , Sikuan Yan , Kevin Qinghong Lin , Zifeng Ding

Deep learning has grown tremendously over recent years, yielding state-of-the-art results in various fields. However, training such models requires huge amounts of data, increasing the computational time and cost. To address this, dataset…

Machine Learning · Computer Science 2023-07-18 Murad Tukan , Alaa Maalouf , Margarita Osadchy

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Computation and Language · Computer Science 2025-10-10 Yuanjie Lyu , Chengyu Wang , Jun Huang , Tong Xu

Recommender systems (RS) have started to employ knowledge distillation, which is a model compression technique training a compact model (student) with the knowledge transferred from a cumbersome model (teacher). The state-of-the-art methods…

Information Retrieval · Computer Science 2021-06-08 Wonbin Kweon , SeongKu Kang , Hwanjo Yu

We present our submission to the BabyLM challenge, aiming to push the boundaries of data-efficient language model pretraining. Our method builds upon deep mutual learning, introducing a student model search for diverse initialization. We…

Computation and Language · Computer Science 2024-11-26 Srikrishna Iyer

Most dataset distillation methods struggle to accommodate large-scale datasets due to their substantial computational and memory requirements. Recent research has begun to explore scalable disentanglement methods. However, there are still…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Zhiheng Ma , Anjia Cao , Funing Yang , Yihong Gong , Xing Wei