English
Related papers

Related papers: DisTaC: Conditioning Task Vectors via Distillation…

200 papers

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

Machine Learning · Computer Science 2024-05-06 Sean Farhat , Deming Chen

In feeds recommendation, the first step is candidate generation. Most of the candidate generation models are based on CTR estimation, which do not consider user's satisfaction with the clicked item. Items with low quality but attractive…

Information Retrieval · Computer Science 2021-02-16 Zhong Zhao , Yanmei Fu , Hanming Liang , Li Ma , Guangyao Zhao , Hongwei Jiang

Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Borui Zhao , Quan Cui , Renjie Song , Jiajun Liang

Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…

Methodology · Statistics 2026-05-28 Luyang Fang , Yongkai Chen , Jiazhang Cai , Ping Ma , Wenxuan Zhong

In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the…

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…

Artificial Intelligence · Computer Science 2026-02-09 Ruichen Zhang , Rana Muhammad Shahroz Khan , Zhen Tan , Dawei Li , Song Wang , Tianlong Chen

Robust multimodal human sensing must overcome the critical challenge of missing modalities. Two principal barriers are the Representation Gap between heterogeneous data and the Contamination Effect from low-quality modalities. These…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Pengcheng Weng , Yanyu Qian , Yangxin Xu , Fei Wang

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Hui Li , Pengfei Yang , Juanyang Chen , Le Dong , Yanxin Chen , Quan Wang

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Simon Vandenhende , Stamatios Georgoulis , Luc Van Gool

Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Yuanhao Zhai , Kevin Lin , Zhengyuan Yang , Linjie Li , Jianfeng Wang , Chung-Ching Lin , David Doermann , Junsong Yuan , Lijuan Wang

Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems. In this work, we propose a…

The huge size of the widely used BERT family models has led to recent efforts about model distillation. The main goal of distillation is to create a task-agnostic pre-trained model that can be fine-tuned on downstream tasks without…

Computation and Language · Computer Science 2021-06-15 Ting-Rui Chiang , Yun-Nung Chen

Graph convolutional networks have made great progress in graph-based semi-supervised learning. Existing methods mainly assume that nodes connected by graph edges are prone to have similar attributes and labels, so that the features smoothed…

Machine Learning · Computer Science 2022-06-13 Yating Ren , Junzhong Ji , Lingfeng Niu , Minglong Lei

Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student…

Machine Learning · Computer Science 2021-05-21 Abdolmaged Alkhulaifi , Fahad Alsahli , Irfan Ahmad

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Computer Vision and Pattern Recognition · Computer Science 2017-10-24 Chong Wang , Xipeng Lan , Yangang Zhang

Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Thanh Nguyen-Duc , He Zhao , Jianfei Cai , Dinh Phung

Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation. However, applying DiTs to molecules introduces…

Machine Learning · Computer Science 2025-11-12 J. Thorben Frank , Winfried Ripken , Gregor Lied , Klaus-Robert Müller , Oliver T. Unke , Stefan Chmiela

Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…

Machine Learning · Computer Science 2025-05-23 Zhixu Silvia Tao , Kasper Vinken , Hao-Wei Yeh , Avi Cooper , Xavier Boix