English
Related papers

Related papers: MARBLE: Multi-Aspect Reward Balance for Diffusion …

200 papers

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…

Machine Learning · Computer Science 2026-04-28 Ying-Tu Chen , Wei Hung , Bing-Shu Wu , Zhang-Wei Hong , Ping-Chun Hsieh

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Machine Learning · Computer Science 2026-05-27 Austin Wang , Jiaqi Han , Stefano Ermon , Yisong Yue

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking:…

Machine Learning · Computer Science 2026-05-15 Saba Ahmadi , Prasanna Parthasarathi , Yufei Cui

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world…

Machine Learning · Computer Science 2024-10-29 Yuting Tang , Xin-Qiang Cai , Yao-Xiang Ding , Qiyu Wu , Guoqing Liu , Masashi Sugiyama

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xuexiang Niu , Jinping Tang , Lei Wang , Ge Zhu

Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies have further employed reinforcement learning from verifiable…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Chenglong Wang , Yifu Huo , Yang Gan , Qiaozhi He , Qi Meng , Bei Li , Yan Wang , Junfu Liu , Tianhua Zhou , Jingbo Zhu , Tong Xiao

Reinforcement fine-tuning played an instrumental role in enhancing the instruction-following and reasoning abilities of large language models. In this work, we employ reinforcement fine-tuning for materials design, in which discriminative…

Materials Science · Physics 2026-01-19 Zhendong Cao , Lei Wang

Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based…

Machine Learning · Computer Science 2020-10-13 Shauharda Khadka , Somdeb Majumdar , Santiago Miret , Stephen McAleer , Kagan Tumer

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Machine Learning · Computer Science 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other…

We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Mihir Prabhudesai , Russell Mendonca , Zheyang Qin , Katerina Fragkiadaki , Deepak Pathak

Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Ziyu Liu , Shengyuan Ding , Xinyu Fang , Xuanlang Dai , Penghui Yang , Jianze Liang , Jiaqi Wang , Kai Chen , Dahua Lin , Yuhang Zang

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation…

Machine Learning · Computer Science 2024-10-17 Rui Yang , Xiaoman Pan , Feng Luo , Shuang Qiu , Han Zhong , Dong Yu , Jianshu Chen

Diffusion models excel at generating high-likelihood samples but often require alignment with downstream objectives. Existing fine-tuning methods for diffusion models significantly suffer from reward over-optimization, resulting in…

Machine Learning · Computer Science 2026-03-09 Hyeongyu Kang , Jaewoo Lee , Woocheol Shin , Kiyoung Om , Jinkyoo Park

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

Computation and Language · Computer Science 2026-04-14 Jiashu Yao , Heyan Huang , Zeming Liu , Yuhang Guo

Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…

Machine Learning · Computer Science 2026-05-08 Guangchen Lan , Lian Xiong , Xin Zhou , Hejie Cui , Yuwei Zhang , Mao Li , Zhenyu Shi , Besnik Fetahu , Lihong Li , Xian Li

Text-to-motion generation has advanced with diffusion- and flow-based generative models, yet supervised pretraining remains insufficient to align models with high-level objectives such as semantic consistency, realism, and human preference.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xiaofeng Tan , Wanjiang Weng , Hongsong Wang , Fang Zhao , Xin Geng , Liang Wang

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as…

Machine Learning · Computer Science 2026-02-18 Raphaël Baur , Yannick Metz , Maria Gkoulta , Mennatallah El-Assady , Giorgia Ramponi , Thomas Kleine Buening