English
Related papers

Related papers: Variational Best-of-N Alignment

200 papers

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Artificial Intelligence · Computer Science 2025-03-19 Anukriti Singh , Amisha Bhaskar , Peihong Yu , Souradip Chakraborty , Ruthwik Dasyam , Amrit Bedi , Pratap Tokekar

Large language models (LLMs) have emerged as promising general-purpose solvers for combinatorial optimization (CO), yet they fundamentally lack mechanisms to guarantee solution feasibility which is critical for real-world deployment. In…

Artificial Intelligence · Computer Science 2026-02-03 Yang Liu , Chuan Zhou , Yancheng Chen , Shuai Zhang , Xixun Lin , Xiaoqing Wang

In this work, we investigate the merits of explicitly optimizing for inference time algorithmic performance during model training. We show how optimizing for inference time performance can improve overall model efficacy. We consider generic…

Machine Learning · Computer Science 2025-08-19 Yunhao Tang , Kunhao Zheng , Gabriel Synnaeve , Rémi Munos

Dynamical generative models that produce samples through an iterative process, such as Flow Matching and denoising diffusion models, have seen widespread use, but there have not been many theoretically-sound methods for improving these…

Machine Learning · Computer Science 2025-01-08 Carles Domingo-Enrich , Michal Drozdzal , Brian Karrer , Ricky T. Q. Chen

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a…

Machine Learning · Computer Science 2018-03-08 Francesco Locatello , Rajiv Khanna , Joydeep Ghosh , Gunnar Rätsch

Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional weight space. We introduce functional variational…

Machine Learning · Computer Science 2019-03-15 Shengyang Sun , Guodong Zhang , Jiaxin Shi , Roger Grosse

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Machine Learning · Computer Science 2025-10-21 Archie Chaudhury

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct backpropagation achieve considerable success in maximizing rewards, they often suffer from…

Machine Learning · Computer Science 2026-03-09 Jaewoo Lee , Minsu Kim , Sanghyeok Choi , Inhyuck Song , Sujin Yun , Hyeongyu Kang , Woocheol Shin , Taeyoung Yun , Kiyoung Om , Jinkyoo Park

Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the token inputs of Large Language Models (LLMs). However, their…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Kevin Y. Li , Sachin Goyal , Joao D. Semedo , J. Zico Kolter

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…

Machine Learning · Computer Science 2022-01-04 Markus Peschl , Arkady Zgonnikov , Frans A. Oliehoek , Luciano C. Siebert

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised…

Computation and Language · Computer Science 2023-12-27 Chunpu Xu , Steffi Chern , Ethan Chern , Ge Zhang , Zekun Wang , Ruibo Liu , Jing Li , Jie Fu , Pengfei Liu

An emerging paradigm in vision-and-language navigation (VLN) is the use of history-aware multi-modal transformer models. Given a language instruction, these models process observation and navigation history to predict the most appropriate…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Dongwoo Kang , Akhil Perincherry , Zachary Coalson , Aiden Gabriel , Stefan Lee , Sanghyun Hong

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning (RL), and often an efficient approach to solving (or approximating the solution to) complex optimal control…

Optimization and Control · Mathematics 2019-03-19 Andrey Bernstein , Yue Chen , Marcello Colombino , Emiliano Dall'Anese , Prashant Mehta , Sean Meyn

Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy…

Artificial Intelligence · Computer Science 2020-06-02 Jeiyoon Park , Chanhee Lee , Kuekyeng Kim , Heuiseok Lim

The k-nearest neighbors (k-NN) classification rule has proven extremely successful in countless many computer vision applications. For example, image categorization often relies on uniform voting among the nearest prototypes in the space of…

Computer Vision and Pattern Recognition · Computer Science 2010-01-11 Paolo Piro , Richard Nock , Frank Nielsen , Michel Barlaud

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

Consider a collection of competing machine learning algorithms. Given their performance on a benchmark of datasets, we would like to identify the best performing algorithm. Specifically, which algorithm is most likely to rank highest on a…

Machine Learning · Computer Science 2025-08-08 Amichai Painsky