English
Related papers

Related papers: Guiding Distribution Matching Distillation with Gr…

200 papers

Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods…

Machine Learning · Computer Science 2026-01-06 Shangzhe Li , Zhiao Huang , Hao Su

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…

Computation and Language · Computer Science 2024-02-19 Yongqi Li , Zhen Zhang , Wenjie Wang , Liqiang Nie , Wenjie Li , Tat-Seng Chua

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between…

Machine Learning · Computer Science 2025-05-27 Chen Jia

In modern large language models (LLMs), LLM alignment is of crucial importance and is typically achieved through methods such as reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO). However, in most…

Computation and Language · Computer Science 2025-07-24 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Xiang Gu , Liming Lu , Xu Zheng , Anan Du , Yongbin Zhou , Shuchao Pang

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Hyejin Park , Dongbo Min

Diffusion Models (DMs) have achieved great success in image generation and other fields. By fine sampling through the trajectory defined by the SDE/ODE solver based on a well-trained score model, DMs can generate remarkable high-quality…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Bowen Zheng , Tianming Yang

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xiyuan Wang , Muhan Zhang

Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, guiding diffusion models on graphs under arbitrary reward…

Machine Learning · Computer Science 2025-05-27 Victor M. Tenorio , Nicolas Zilberstein , Santiago Segarra , Antonio G. Marques

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

Robotics · Computer Science 2023-10-16 Jinning Li , Xinyi Liu , Banghua Zhu , Jiantao Jiao , Masayoshi Tomizuka , Chen Tang , Wei Zhan

In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A naive \textit{GenDD} baseline encounters two major…

Machine Learning · Computer Science 2025-07-22 Jiequan Cui , Beier Zhu , Qingshan Xu , Xiaogang Xu , Pengguang Chen , Xiaojuan Qi , Bei Yu , Hanwang Zhang , Richang Hong

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Zelong Zeng , Fan Yang , Zheng Wang , Shin'ichi Satoh

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Machine Learning · Computer Science 2026-05-12 Khouloud Saadi , Di Wang

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are…

Machine Learning · Computer Science 2023-04-18 Lei Zhang , Jie Zhang , Bowen Lei , Subhabrata Mukherjee , Xiang Pan , Bo Zhao , Caiwen Ding , Yao Li , Dongkuan Xu

Diffusion models, such as Stable Diffusion (SD), offer the ability to generate high-resolution images with diverse features, but they come at a significant computational and memory cost. In classifier-free guided diffusion models, prolonged…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Pareesa Ameneh Golnari

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span…

Machine Learning · Computer Science 2025-02-04 Saeed Vahidian , Mingyu Wang , Jianyang Gu , Vyacheslav Kungurtsev , Wei Jiang , Yiran Chen

While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…

Machine Learning · Computer Science 2024-12-09 Sirui Xie , Zhisheng Xiao , Diederik P Kingma , Tingbo Hou , Ying Nian Wu , Kevin Patrick Murphy , Tim Salimans , Ben Poole , Ruiqi Gao

Intrinsic motivation, inspired by the psychology of developmental learning in infants, stimulates exploration in agents without relying solely on sparse external rewards. Existing methods in reinforcement learning like Random Network…

Machine Learning · Computer Science 2024-10-03 Mohammadamin Davoodabadi , Negin Hashemi Dijujin , Mahdieh Soleymani Baghshah

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
‹ Prev 1 3 4 5 6 7 10 Next ›