English
Related papers

Related papers: Advantage-Guided Diffusion for Model-Based Reinfor…

200 papers

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures, such as using…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Daehee Park , Monu Surana , Pranav Desai , Ashish Mehta , Reuben MV John , Kuk-Jin Yoon

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Zhicong Tang , Jianmin Bao , Dong Chen , Baining Guo

Recent advances in diffusion models have demonstrated their strong capabilities in generating high-fidelity samples from complex distributions through an iterative refinement process. Despite the empirical success of diffusion models in…

Robotics · Computer Science 2024-07-03 Chaoyi Pan , Zeji Yi , Guanya Shi , Guannan Qu

Offline reinforcement learning (RL) learns policies from fixed datasets without online interactions, but suffers from distribution shift, causing inaccurate evaluation and overestimation of out-of-distribution (OOD) actions. Existing…

Machine Learning · Computer Science 2025-10-07 Xuyang Chen , Keyu Yan , Wenhan Cao , Lin Zhao

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Machine Learning · Computer Science 2021-03-02 Zichuan Lin , Garrett Thomas , Guangwen Yang , Tengyu Ma

Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabilities and flexibility. However, current motion diffusion models face two major limitations: a…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Yifei Liu , Changxing Ding , Ling Guo , Huaiguang Jiang , Qiong Cao

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Haotian Xue , Alexandre Araujo , Bin Hu , Yongxin Chen

Deep reinforcement learning (DRL) has long been a promising solution for sequential resource management in wireless networks. However, conventional DRL methods are fundamentally limited by their reliance on unimodal policy distributions,…

We propose enforcing constraints on Model-Based Diffusion by introducing emerging barrier functions inspired by interior point methods. We demonstrate that the standard Model-Based Diffusion algorithm can lead to catastrophic performance…

Robotics · Computer Science 2026-03-10 Raghav Mishra , Ian R. Manchester

Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process. However, the current solvers, which recursively apply a reverse diffusion step…

Machine Learning · Computer Science 2024-05-21 Hyungjin Chung , Byeongsu Sim , Dohoon Ryu , Jong Chul Ye

Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative sampling process required for synthesis is very…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Yeongmin Kim , Sotiris Anagnostidis , Yuming Du , Edgar Schönfeld , Jonas Kohler , Markos Georgopoulos , Albert Pumarola , Ali Thabet , Artsiom Sanakoyeu

World Model-based Reinforcement Learning (WMRL) enables sample efficient policy learning by reducing the need for online interactions which can potentially be costly and unsafe, especially for autonomous driving. However, existing world…

Robotics · Computer Science 2025-03-11 Anant Garg , K Madhava Krishna

Designing de novo 3D molecules with desirable properties remains a fundamental challenge in drug discovery and molecular engineering. While diffusion models have demonstrated remarkable capabilities in generating high-quality 3D molecular…

Machine Learning · Computer Science 2026-01-15 Lianghong Chen , Dongkyu Eugene Kim , Mike Domaratzki , Pingzhao Hu

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

Diffusion models represent the state-of-the-art for solving inverse problems such as image restoration tasks. Diffusion-based inverse solvers incorporate a likelihood term to guide prior sampling, generating data consistent with the…

Machine Learning · Computer Science 2026-03-03 Bahareh Tolooshams , Aditi Chandrashekar , Rayhan Zirvi , Abbas Mammadov , Jiachen Yao , Chuwei Wang , Anima Anandkumar

Diffusion-based Handwritten Text Generation (HTG) approaches achieve impressive results on frequent, in-vocabulary words observed at training time and on regular styles. However, they are prone to memorizing training samples and often…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Konstantina Nikolaidou , George Retsinas , Giorgos Sfikas , Silvia Cascianelli , Rita Cucchiara , Marcus Liwicki

By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories…

We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from…

Machine Learning · Computer Science 2024-06-03 Bartosz Cywiński , Kamil Deja , Tomasz Trzciński , Bartłomiej Twardowski , Łukasz Kuciński

Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has enabled learning a collection of behaviorally diverse, high performing policies. However, these methods typically involve storing thousands of policies, which results…

Machine Learning · Computer Science 2023-06-27 Shashank Hegde , Sumeet Batra , K. R. Zentner , Gaurav S. Sukhatme
‹ Prev 1 4 5 6 7 8 10 Next ›