English
Related papers

Related papers: Privileged Features Distillation at Taobao Recomme…

200 papers

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

World action models jointly predict future video and action during training, raising an open question about what role the future-prediction branch actually plays. A recent finding shows that this branch can be removed at inference with…

Robotics · Computer Science 2026-05-05 Pengcheng Fang , Hongli Chen , Xiaohao Cai

Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…

Machine Learning · Computer Science 2026-03-24 Jing Liu , Zhenchao Ma , Han Yu , Bobo Ju , Wenliang Yang , Chengfang Li , Bo Hu , Liang Song

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…

Machine Learning · Computer Science 2020-08-04 Yushuo Guan , Pengyu Zhao , Bingxuan Wang , Yuanxing Zhang , Cong Yao , Kaigui Bian , Jian Tang

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Machine Learning · Computer Science 2026-03-26 Ken Ding

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Machine Learning · Computer Science 2025-10-06 Yuda Song , Dhruv Rohatgi , Aarti Singh , J. Andrew Bagnell

Digital textbooks are widely used in various educational contexts, such as university courses and online lectures. Such textbooks yield learning log data that have been used in numerous educational data mining (EDM) studies for student…

Machine Learning · Computer Science 2025-07-22 Shunsuke Yoneda , Valdemar Švábenský , Gen Li , Daisuke Deguchi , Atsushi Shimada

Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary…

Machine Learning · Computer Science 2020-05-20 Pierre-Alexandre Kamienny , Kai Arulkumaran , Feryal Behbahani , Wendelin Boehmer , Shimon Whiteson

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

The task of predicting conversion rates (CVR) lies at the heart of online advertising systems aiming to optimize bids to meet advertiser performance requirements. Even with the recent rise of deep neural networks, these predictions are…

Information Retrieval · Computer Science 2024-01-31 Alex Shtoff , Yohay Kaplan , Ariel Raviv

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Dengyang Jiang , Dongyang Liu , Zanyi Wang , Qilong Wu , Liuzhuozheng Li , Hengzhuang Li , Xin Jin , David Liu , Changsheng Lu , Zhen Li , Bo Zhang , Mengmeng Wang , Steven Hoi , Peng Gao , Harry Yang

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chaoyang Wang , Yunhai Tong

Click-Through Rate (CTR) prediction plays a core role in recommender systems, serving as the final-stage filter to rank items for a user. The key to addressing the CTR task is learning feature interactions that are useful for prediction,…

Information Retrieval · Computer Science 2023-04-27 Yang Zhang , Tianhao Shi , Fuli Feng , Wenjie Wang , Dingxian Wang , Xiangnan He , Yongdong Zhang

In online advertising, conventional post-click conversion rate (CVR) estimation models are trained using clicked samples. However, during online serving the models need to estimate for all impression ads, leading to the sample selection…

Information Retrieval · Computer Science 2022-01-21 Zixuan Xu , Penghui Wei , Weimin Zhang , Shaoguo Liu , Liang Wang , Bo Zheng

Post-click conversion rate (CVR) estimation is a critical task in e-commerce recommender systems. This task is deemed quite challenging under the industrial setting with two major issues: 1) selection bias caused by user self-selection, and…

Information Retrieval · Computer Science 2020-04-07 Wenhao Zhang , Wentian Bao , Xiao-Yang Liu , Keping Yang , Quan Lin , Hong Wen , Ramin Ramezani

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e.g. in crowdsourcing tasks. Intuitively, not all workers are equally reliable but, if the less reliable ones could be eliminated, then…

Machine Learning · Statistics 2017-11-28 Vincent Zhao , Steven W. Zucker

Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…

Large foundation models trained on extensive datasets demonstrate strong zero-shot capabilities in various domains. To replicate their success when data and model size are constrained, knowledge distillation has become an established tool…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Niclas Popp , Kevin Alexander Laube , Matthias Hein , Lukas Schott