English
Related papers

Related papers: The tractability landscape of diffusion alignment:…

200 papers

Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because…

Machine Learning · Computer Science 2022-03-15 Ju-Seung Byun , Andrew Perrault

Inference-time scaling methods rely on Process Reward Models (PRMs), which are often poorly calibrated and overestimate success probabilities. We propose, to our knowledge, the first use of conditional optimal transport for calibrating…

Machine Learning · Computer Science 2026-05-13 Rachel Ma , Dylan Hadfield-Menell , Kristjan Greenewald

We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its weights. Recent Sequential Monte Carlo (SMC)-based steering methods approximate…

Machine Learning · Computer Science 2026-05-26 Weixin Wang , Yu Yang , Wei Deng , Pan Xu

Diffusion alignment adapts pretrained diffusion models to sample from reward-tilted distributions along the denoising trajectory. This process naturally admits a Sequential Monte Carlo (SMC) interpretation, where the denoising model acts as…

Machine Learning · Computer Science 2026-02-13 Zijing Ou , Jacob Si , Junyi Zhu , Ondrej Bohdal , Mete Ozay , Taha Ceritli , Yingzhen Li

We study how to exploit dense simulator-defined rewards in vision-based autonomous driving without inheriting their misalignment with deployment metrics. In realistic simulators such as CARLA, privileged state (e.g., lane geometry,…

Robotics · Computer Science 2025-12-30 Feeza Khan Khanzada , Jaerock Kwon

Optimal transportation theory and the related $p$-Wasserstein distance ($W_p$, $p\geq 1$) are widely-applied in statistics and machine learning. In spite of their popularity, inference based on these tools has some issues. For instance, it…

Statistics Theory · Mathematics 2024-03-01 Yiming Ma , Hang Liu , Davide La Vecchia , Metthieu Lerasle

Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need…

Machine Learning · Computer Science 2021-03-15 Alex J. Chan , Mihaela van der Schaar

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Canyu Zhao , Hao Chen , Yunze Tong , Yu Qiao , Jiacheng Li , Chunhua Shen

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…

Machine Learning · Computer Science 2024-10-11 Xudong Yu , Chenjia Bai , Haoran He , Changhong Wang , Xuelong Li

Preference-based Reinforcement Learning (PbRL) entails a variety of approaches for aligning models with human intent to alleviate the burden of reward engineering. However, most previous PbRL work has not investigated the robustness to…

Machine Learning · Computer Science 2025-06-17 Sara Rajaram , R. James Cotton , Fabian H. Sinz

Let $p$ denote a generative language model. Let $r$ denote a reward model that returns a scalar that captures the degree at which a draw from $p$ is preferred. The goal of language model alignment is to alter $p$ to a new distribution…

Machine Learning · Computer Science 2024-04-03 Joy Qiping Yang , Salman Salamatian , Ziteng Sun , Ananda Theertha Suresh , Ahmad Beirami

Offline preference-based reinforcement learning (PbRL) mitigates the need for reward definition, aligning with human preferences via preference-driven reward feedback without interacting with the environment. However, trajectory-wise…

Machine Learning · Computer Science 2025-09-25 Teng Pang , Bingzheng Wang , Guoqiang Wu , Yilong Yin

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing…

Machine Learning · Computer Science 2026-05-14 Jiaming Li , Chenyu Zhu , Nanxi Yi , Youjun Bao , Li Sun , Quanying Lv , Xiang Fang , Daizong Liu , Jianjun Li , Kun He , Bowen Zhou , Zhiyuan Ma

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Machine Learning · Computer Science 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent. This paper studies a test-time scaling method that enables sampling from regions with higher…

Machine Learning · Computer Science 2026-02-04 Yeongmin Kim , Donghyeok Shin , Byeonghu Na , Minsang Park , Richard Lee Kim , Il-Chul Moon

Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-based image restoration models is suboptimal, as the objective…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xiaogang Xu , Ruihang Chu , Jian Wang , Kun Zhou , Wenjie Shu , Harry Yang , Ser-Nam Lim , Hao Chen , Liang Lin

In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to…

Machine Learning · Computer Science 2014-05-28 Sridhar Mahadevan , Bo Liu , Philip Thomas , Will Dabney , Steve Giguere , Nicholas Jacek , Ian Gemp , Ji Liu

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in…

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton