English
Related papers

Related papers: Diversity-Rewarded CFG Distillation

200 papers

The success of text-to-image (T2I) generation models has spurred a proliferation of numerous model checkpoints fine-tuned from the same base model on various specialized datasets. This overwhelming specialized model production introduces…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Tianhui Song , Weixin Feng , Shuai Wang , Xubin Li , Tiezheng Ge , Bo Zheng , Limin Wang

Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily…

Information Retrieval · Computer Science 2025-11-25 Yejing Wang , Shengyu Zhou , Jinyu Lu , Qidong Liu , Xinhang Li , Wenlin Zhang , Feng Li , Pengjie Wang , Jian Xu , Bo Zheng , Xiangyu Zhao

Feature generation can significantly enhance learning outcomes, particularly for tasks with limited data. An effective way to improve feature generation is to expand the current feature space using existing features and enriching the…

Computation and Language · Computer Science 2025-11-11 Xinhao Zhang , Jinghan Zhang , Fengran Mo , Dakshak Keerthi Chandra , Yu-Zhong Chen , Fei Xie , Kunpeng Liu

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…

Machine Learning · Computer Science 2026-02-24 David Li , Nikita Gushchin , Dmitry Abulkhanov , Eric Moulines , Ivan Oseledets , Maxim Panov , Alexander Korotin

Knowledge distillation has made remarkable achievements in model compression. However, most existing methods require the original training data, which is usually unavailable due to privacy and security issues. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Xinyi Yu , Ling Yan , Yang Yang , Libo Zhou , Linlin Ou

The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other extreme, distillation offers dense supervision but requires…

Machine Learning · Computer Science 2026-02-12 Yuda Song , Lili Chen , Fahim Tajwar , Remi Munos , Deepak Pathak , J. Andrew Bagnell , Aarti Singh , Andrea Zanette

High-resolution image synthesis with diffusion models often suffers from energy instabilities and guidance artifacts that degrade visual quality. We analyze the latent energy landscape during sampling and propose adaptive classifier-free…

Graphics · Computer Science 2025-12-12 Ankit Sanjyal

A fascinating aspect of nature lies in its ability to produce a large and diverse collection of organisms that are all high-performing in their niche. By contrast, most AI algorithms focus on finding a single efficient solution to a given…

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Gaussian mixture modeling with a closed-form solution, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Chubin Chen , Jiashu Zhu , Xiaokun Feng , Nisha Huang , Chen Zhu , Meiqi Wu , Fangyuan Mao , Jiahong Wu , Xiangxiang Chu , Xiu Li

The powerful generalization of Vision-Language-Action (VLA) models is bottlenecked by their heavy reliance on massive, redundant, and unevenly valued datasets, hindering their widespread application. Existing model-centric optimization…

Robotics · Computer Science 2025-11-21 Kewei Chen , Yayu Long , Shuai Li , Mingsheng Shang

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by…

Machine Learning · Computer Science 2021-03-30 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Recent advancements in large language models (LLMs) have demonstrated remarkable text generation capabilities. However, controlling specific attributes of generated text remains challenging without architectural modifications or extensive…

Computation and Language · Computer Science 2025-11-18 Yu Li , Zhe Yang , Yi Huang , Xin Liu , Guilin Qi

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve…

Multimedia · Computer Science 2026-03-27 Nailei Hei , Qianyu Guo , Zihao Wang , Yan Wang , Haofen Wang , Wenqiang Zhang

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Geon Yeong Park , Sang Wan Lee , Jong Chul Ye

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Machine Learning · Statistics 2015-10-09 George Papamakarios

Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often reduces sample diversity. Using tools from statistical physics, we analyze the emergence of generative distortions induced by…

Machine Learning · Statistics 2026-05-11 Enrico Ventura , Beatrice Achilli , Luca Ambrogioni , Carlo Lucibello

Pre-trained multilingual language models (LMs) have achieved state-of-the-art results in cross-lingual transfer, but they often lead to an inequitable representation of languages due to limited capacity, skewed pre-training data, and…

Computation and Language · Computer Science 2021-06-08 Simran Khanuja , Melvin Johnson , Partha Talukdar

Recently, innovative model aggregation methods based on knowledge distillation (KD) have been proposed for federated learning (FL). These methods not only improved the robustness of model aggregation over heterogeneous learning environment,…

Machine Learning · Computer Science 2023-12-29 Ho Man Kwan , Shenghui Song

Our paper addresses the problem of models struggling to learn diverse features, due to either forgetting previously learned features or failing to learn new ones. To overcome this problem, we introduce Diverse Feature Learning (DFL), a…

Artificial Intelligence · Computer Science 2024-04-01 Sejik Park

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min