English
Related papers

Related papers: When Preference Labels Fall Short: Aligning Diffus…

200 papers

Dimensionality reduction is often used as an initial step in data exploration, either as preprocessing for classification or regression or for visualization. Most dimensionality reduction techniques to date are unsupervised; they do not…

Machine Learning · Statistics 2020-06-17 Jake S. Rhodes , Adele Cutler , Guy Wolf , Kevin R. Moon

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two…

Machine Learning · Computer Science 2019-11-20 Qian Wang , Toby P. Breckon

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Diffusion models without guidance generate very unrealistic samples. Guidance is used ubiquitously, and previous research has attributed its effect to low-temperature sampling that improves quality by trading off diversity. However, this…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Shanchuan Lin , Xiao Yang

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Yang Zhang , Teoh Tze Tzun , Lim Wei Hern , Tiviatis Sim , Kenji Kawaguchi

Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Dohyun Kim , Seungwoo Lyu , Seung Wook Kim , Paul Hongsuck Seo

As AI systems approach superhuman capabilities, scalable oversight increasingly relies on LLM-as-a-judge frameworks where models evaluate and guide each other's training. A core assumption is that binary preference labels provide only…

Machine Learning · Computer Science 2026-03-13 Isotta Magistrali , Frédéric Berdoz , Sam Dauncey , Roger Wattenhofer

Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we…

Machine Learning · Computer Science 2025-03-05 Dongyoung Kim , Kimin Lee , Jinwoo Shin , Jaehyung Kim

This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities,…

Artificial Intelligence · Computer Science 2025-01-22 Masatoshi Uehara , Yulai Zhao , Chenyu Wang , Xiner Li , Aviv Regev , Sergey Levine , Tommaso Biancalani

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…

Machine Learning · Computer Science 2026-02-03 Yao Zhao , Kwang-Sung Jun

Label distribution (LD) uses the description degree to describe instances, which provides more fine-grained supervision information when learning with label ambiguity. Nevertheless, LD is unavailable in many real-world applications. To…

Machine Learning · Computer Science 2023-03-22 Zhiqiang Kou , Yuheng Jia , Jing Wang , Boyu Shi , Xin Geng

In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Sachin Chhabra , Hemanth Venkateswara , Baoxin Li

Diffusion models have emerged as the principal paradigm for generative modeling across various domains. During training, they learn the score function, which in turn is used to generate samples at inference. They raise a basic yet unsolved…

Machine Learning · Computer Science 2025-10-03 Kiwhan Song , Jaeyeon Kim , Sitan Chen , Yilun Du , Sham Kakade , Vincent Sitzmann

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

Artificial Intelligence · Computer Science 2016-09-20 Russell Stewart , Stefano Ermon

We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an annotator provides fine-grained feedback by marking ``liked'' and ``disliked''…

Computation and Language · Computer Science 2025-12-30 Sky CH-Wang , Justin Svegliato , Helen Appel , Jason Eisner

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Machine Learning · Computer Science 2025-02-05 Jie Ren , Yuhang Zhang , Dongrui Liu , Xiaopeng Zhang , Qi Tian

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Machine Learning · Computer Science 2024-11-12 Zhuotong Chen , Fang Liu , Jennifer Zhu , Wanyu Du , Yanjun Qi

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Yinan Zhang , Eric Tzeng , Yilun Du , Dmitry Kislyuk

Contemporary sequential recommendation methods are becoming more complex, shifting from classification to a diffusion-guided generative paradigm. However, the quality of guidance in the form of user information is often compromised by…

Information Retrieval · Computer Science 2026-02-16 Qilong Yan , Yifei Xing , Dugang Liu , Jingpu Duan , Jian Yin

Shortcut learning is when a model -- e.g. a cardiac disease classifier -- exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predict the target label based on the shortcut rather than real…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Nina Weng , Paraskevas Pegios , Eike Petersen , Aasa Feragen , Siavash Bigdeli