English
Related papers

Related papers: Relative Density Ratio Optimization for Stable and…

200 papers

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated,…

Computation and Language · Computer Science 2024-06-07 Afra Amini , Tim Vieira , Ryan Cotterell

Moment-based distributionally robust optimization (DRO) provides an optimization framework to integrate statistical information with traditional optimization approaches. Under this framework, one assumes that the underlying joint…

Optimization and Control · Mathematics 2023-11-01 Shiyi Jiang , Jianqiang Cheng , Kai Pan , Zuo-Jun Max Shen

We consider optimal decision-making problems in an uncertain environment. In particular, we consider the case in which the distribution of the input is unknown, yet there is abundant historical data drawn from the distribution. In this…

Optimization and Control · Mathematics 2014-10-03 Zizhuo Wang , Peter Glynn , Yinyu Ye

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Zhou Jiang , Yandong Wen , Zhen Liu

Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data…

Machine Learning · Computer Science 2025-02-25 Zekun Wang , Mingyang Yi , Shuchen Xue , Zhenguo Li , Ming Liu , Bing Qin , Zhi-Ming Ma

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Amirabbas Afzali , Borna Khodabandeh , Ali Rasekh , Mahyar JafariNodeh , Sepehr kazemi , Simon Gottschalk

A measure of similarity between text embeddings can be considered adequate only if it adheres to the human perception of similarity between texts. In this paper, we introduce the distance-to-distance ratio (DDR), a novel measure of…

Computation and Language · Computer Science 2026-01-27 Abdullah Qureshi , Kenneth Rice , Alexander Wolpert

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Machine Learning · Computer Science 2024-07-01 William Muldrew , Peter Hayes , Mingtian Zhang , David Barber

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Kaiwen Zheng , Yongxin Chen , Huayu Chen , Guande He , Ming-Yu Liu , Jun Zhu , Qinsheng Zhang

The emergence of large Vision Language Models (VLMs) has broadened the scope and capabilities of single-modal Large Language Models (LLMs) by integrating visual modalities, thereby unlocking transformative cross-modal applications in a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Shuo Xing , Peiran Li , Yuping Wang , Ruizheng Bai , Yueqi Wang , Chan-Wei Hu , Chengxuan Qian , Huaxiu Yao , Zhengzhong Tu

Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional uncertainty size is often shown to correspond to the…

Machine Learning · Statistics 2021-05-12 Jose Blanchet , Yang Kang , Fan Zhang , Fei He , Zhangyi Hu

Direct Preference Optimization (DPO) has recently emerged as a popular approach to improve reinforcement learning with human feedback (RLHF), leading to better techniques to fine-tune large language models (LLM). A weakness of DPO, however,…

Machine Learning · Computer Science 2025-04-21 Haoxian Chen , Hanyang Zhao , Henry Lam , David Yao , Wenpin Tang

Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations --…

Computation and Language · Computer Science 2025-05-12 Julia Shuieh , Prasann Singhal , Apaar Shanker , John Heyer , George Pu , Samuel Denton

Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech…

Computation and Language · Computer Science 2024-11-12 Cindy Tseng , Yun Tang , Vijendra Raj Apsingekar

A prominent family of methods for learning data distributions relies on density ratio estimation (DRE), where a model is trained to $\textit{classify}$ between data samples and samples from some reference distribution. DRE-based models can…

Machine Learning · Computer Science 2024-11-01 Shahar Yadin , Noam Elata , Tomer Michaeli

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Shaomeng Wang , He Wang , Xiaolu Wei , Longquan Dai , Jinhui Tang

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Computation and Language · Computer Science 2025-04-16 Zhihao Xu , Yongqi Tong , Xin Zhang , Jun Zhou , Xiting Wang

The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective. Even though this provides adequate results in most cases, it comes with several shortcomings. The methods…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Nikolaos Passalis , Anastasios Tefas

Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting…

Computation and Language · Computer Science 2025-02-10 Zhenglin Zhou , Xiaobo Xia , Fan Ma , Hehe Fan , Yi Yang , Tat-Seng Chua

Domain Adaptation (DA) has recently received significant attention due to its potential to adapt a learning model across source and target domains with mismatched distributions. Since DA methods rely exclusively on the given source and…

Machine Learning · Statistics 2022-11-01 Akram S. Awad , George K. Atia
‹ Prev 1 8 9 10 Next ›