English
Related papers

Related papers: Diffusion-State Policy Optimization for Masked Dif…

200 papers

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a critical aspect is…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xiaoyin Xu , Min Zhang

3D generation has rapidly accelerated in the past decade owing to the progress in the field of generative modeling. Score Distillation Sampling (SDS) based rendering has improved 3D asset generation to a great extent. Further, the recent…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Aradhya N. Mathur , Phu Pham , Aniket Bera , Ojaswa Sharma

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this…

Machine Learning · Computer Science 2026-04-17 Xiaoyi Dong , Xi Sheryl Zhang , Jian Cheng

While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic…

Machine Learning · Computer Science 2025-10-10 Yihong Luo , Tianyang Hu , Jing Tang

Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR)…

Computation and Language · Computer Science 2025-06-04 Siyan Zhao , Devaansh Gupta , Qinqing Zheng , Aditya Grover

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…

Machine Learning · Computer Science 2026-02-17 Subham Sekhar Sahoo , Jean-Marie Lemercier , Zhihan Yang , Justin Deschenaux , Jingyu Liu , John Thickstun , Ante Jukic

Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, and alignment. Using pairs of preferred and dispreferred…

Computation and Language · Computer Science 2024-07-04 Arka Pal , Deep Karkhanis , Samuel Dooley , Manley Roberts , Siddartha Naidu , Colin White

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

Machine Learning · Computer Science 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang

Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to…

Machine Learning · Computer Science 2023-05-23 Long Yang , Zhixiong Huang , Fenghao Lei , Yucun Zhong , Yiming Yang , Cong Fang , Shiting Wen , Binbin Zhou , Zhouchen Lin

In recent years, large-scale pre-trained diffusion models have demonstrated their outstanding capabilities in image and video generation tasks. However, existing models tend to produce visual objects commonly found in the training dataset,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Changgu Chen , Libing Yang , Xiaoyan Yang , Lianggangxu Chen , Gaoqi He , CHangbo Wang , Yang Li

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment,…

Machine Learning · Computer Science 2026-05-11 Hongbo Jin , Rongpeng Zhu , Zhongjing Du , Xu Jiang , Jingqi Tian , Qiaoman Zhang , Jiayu Ding

While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative…

Computation and Language · Computer Science 2025-06-10 Dimitri von Rütte , Janis Fluri , Yuhui Ding , Antonio Orvieto , Bernhard Schölkopf , Thomas Hofmann

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Machine Learning · Computer Science 2025-02-05 Jie Ren , Yuhang Zhang , Dongrui Liu , Xiaopeng Zhang , Qi Tian

Recent advancements in human preference optimization, originally developed for Large Language Models (LLMs), have shown significant potential in improving text-to-image diffusion models. These methods aim to learn the distribution of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Amir Saeidi , Yiran Luo , Agneet Chatterjee , Shamanthak Hegde , Bimsara Pathiraja , Yezhou Yang , Chitta Baral

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Runtao Liu , Haoyu Wu , Zheng Ziqiang , Chen Wei , Yingqing He , Renjie Pi , Qifeng Chen

Test-time policy optimization enables large language models (LLMs) to adapt to distribution shifts by leveraging feedback from self-generated rollouts. However, existing methods rely on fixed-budget majority voting to estimate rewards,…

Machine Learning · Computer Science 2025-12-03 Youkang Wang , Jian Wang , Rubing Chen , Tianyi Zeng , Xiao-Yong Wei , Qing Li

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

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Computation and Language · Computer Science 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignment ignores which…

Artificial Intelligence · Computer Science 2026-05-27 Ankur Samanta , Akshayaa Magesh , Ayush Jain , Youliang Yu , Daniel Jiang , Kavosh Asadi , Kaveh Hassani , Paul Sajda , Jalaj Bhandari , Yonathan Efroni

Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However, in highly nonlinear and hybrid discrete-continuous domains, the resulting optimization…

Artificial Intelligence · Computer Science 2026-05-11 Yuval Aroosh , Ayal Taitler