Diffusion Model Alignment

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 131

All topics

Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Jul 7, 2026Sakuya Ota, Qing Yu, Kent Fujiwara +2Diffusion Model Alignment Text-to-Motion Generation
Institute of Science Tokyo, Tokyo, Japan · LY Corporation, Tokyo, Japan · National Institute of Informatics (NII), Tokyo, Japan
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
Jul 7, 2026Jinkyu Kim, Jinyoung Choi, Bohyung HanDiffusion Model Alignment Direct Preference Optimization
1ECE & 2IPAI, Seoul National University, Korea · 3AIGS, Ulsan National Institute of Science and Technology, Korea
Reward Lightning: Fast Video Generation via Homologous Preference Distillation
Jul 4, 2026Jiaxiang Cheng, Bing Ma, Xuhua Ren +4Diffusion Model Alignment Reward Modeling
Tencent Hunyuan, China
Self-Improving Diffusion Classifiers with Minority Preference Optimization
Jul 4, 2026Hyunsoo Kim, Jungmyung Wi, Soobin Um +2Diffusion Model Alignment Long-Tailed Classification
1Korea University · 2Kook Min University · 3Kyung Hee University
FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers
Jul 3, 2026Chen Chen, Yuanmin Huang, Zhenfei Zhang +5Diffusion Model Alignment Diffusion Transformer
Fudan University Shanghai, China · East China University of Science and Technology Shanghai, China
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Jul 2, 2026Dengyang Jiang, Mengmeng Wang, Harry Yang +1Diffusion Model Alignment Data Augmentation
1The Hong Kong University of Science and Technology · 2Zhejiang University of Technology · 3Baidu Inc.
PAPA: Online Personalized Active Preference Alignment
Jul 1, 2026Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas +2Diffusion Model Alignment Diffusion Model Fine-Tuning
Washington University in St. Louis · Oak Ridge National Laboratory
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Jul 1, 2026Adeel Yousaf, Soumik Ghosh, James Beetham +2Diffusion Model Alignment Representation Learning
Institute of Artificial Intelligence University of Central Florida, Orlando, United States
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Jun 23, 2026Haorui Ji, Weizhe Liu, Hongdong Li +1Diffusion Model Alignment 3D Gaussian Splatting
The Australian National University · ByteDance
SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models
Jun 22, 2026Hongxiang Li, Hongxu Chen, Chenyang Zhu +5Diffusion Model Alignment Unified Multimodal Models
The Hong Kong University of Science and Technology · Xiaohongshu Inc.
PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models
Jun 22, 2026Ruolan Sun, Pawel PolakDiffusion Model Alignment Inference-Time Language Model Alignment
Stony Brook University
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows
Jun 18, 2026Daniel Gilo, Sven Elflein, Ido Sobol +1Diffusion Model Alignment Diffusion Models for Image Restoration
1Technion · 2NVIDIA · University of Toronto +1
NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
Jun 16, 2026Jisung Hwang, Yunhong Min, Jaihoon Kim +2Diffusion Model Alignment Diffusion Model Guidance
1KAIST · †This work was done in part while the author was a visiting researcher at The University of Tokyo. · 2The University of Tokyo
STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training
Jun 16, 2026Jinjie Shen, Wei Deng, Xian Hu +2Diffusion Model Alignment Compositional T2I Generation
Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering
Jun 15, 2026Rohit Kundu, Arindam Dutta, Sarosij Bose +2Diffusion Model Alignment Video Diffusion Models
University of California, Riverside · YouTube (Google)
GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving
Jun 15, 2026Ziying Song, Caiyan Jia, Lin Liu +3Diffusion Model Alignment End-to-End Autonomous Driving
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University · School of Artificial Intelligence (School of Software), Yanshan University · University of Macau +2
HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities
Jun 12, 2026Yijun Liu, Jie Huang, Zeyue Xue +5Diffusion Model Alignment Multimodal Reward Modeling
Tsinghua University · JD Explore Academy · Peking University +1
PepALD: Macrocyclic Peptide Generation via Autoregressive Latent Diffusion
Jun 12, 2026Junming Zhang, Siyu Yi, Wei Ju +1Diffusion Model Alignment Autoregressive Diffusion
College of Computer Science, Sichuan University, Chengdu, 610065, China · School of Mathematics, Sichuan University, Chengdu, 610065, China · School of Artificial Intelligence, Sichuan University, Chengdu, 610065, China +1
MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
Jun 7, 2026Lianyu Pang, Tianlin Pan, Cheng Da +5Diffusion Model Alignment Diffusion Transformer
The Hong Kong University of Science and Technology · Kuaishou Technology · University of Chinese Academy of Sciences
Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback
Jun 4, 2026Huaisong Zhang, Hao Yu, Yuxuan Zhang +7Diffusion Model Alignment T2I Generation Evaluation
Tsinghua University · University of British Columbia · Vector Institute +2
CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection
Jun 3, 2026Roberto Di Via, Irina Voiculescu, Francesca Odone +1Diffusion Model Alignment Diffusion Model Guidance
MaLGa, DIBRIS, University of Genoa, Italy · Department of Computer Science, University of Oxford, UK
Drifting Preference Optimization for One-Step Generative Models
Jun 1, 2026Zhou Jiang, Yandong Wen, Zhen LiuDiffusion Model Alignment One-Step Generative Modeling
Westlake University · The Chinese University of Hong Kong, Shenzhen
FairGen: Preference-Aligned Diffusion for Demographically Equitable Medical Image Synthesis
Jun 1, 2026Zhimin Li, Ruichen Zhang, Zhen Tan +3Diffusion Model Alignment Synthetic Data Augmentation
University of Pittsburgh, Swanson School of Engineering, Pittsburgh, 15261, USA · 2The University of North Carolina at Chapel Hill, Department of Computer Science, Chapel Hill, 27599, USA · 3Arizona State University, School of Computing and Augmented Intelligence, Tempe, 85281, USA +1
Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
Jun 1, 2026Pengyang Ling, Jiazi Bu, Yujie Zhou +6Diffusion Model Alignment Group Relative Policy Optimization
University of Science and Technology of China, China · Shanghai Jiao Tong University, China · Fudan University, China +3
Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
May 31, 2026Ziyue Lin, Jiahe Hou, Hongyu Xia +6Diffusion Model Alignment Image-to-Image Translation
1The University of Hong Kong · 2Shenyang Institute of Automation, Chinese Academy of Sciences · 3The Chinese University of Hong Kong +1
Improving Visual Representation Alignment Generation with GRPO
May 30, 2026Shentong Mo, Sukmin YunDiffusion Model Alignment Diffusion Transformer
Carnegie Mellon University · Hanyang University
Parallel Tempering Initial Sampling in Inference-Time Reward Alignment
May 29, 2026Myeongjun Oh, Gwangho Kim, Sungyoon LeeDiffusion Model Alignment Markov Chain Monte Carlo
Department of Artificial Intelligence 2Department of Computer Science Hanyang University, Seoul, Korea
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
May 29, 2026Zhiyang Lu, Ming ChengDiffusion Model Alignment Latent Diffusion Models
1Fujian Key Laboratory of Urban Intelligent Sensing and Com · 2Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Min
Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
May 28, 2026Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon +1Diffusion Model Alignment Text-Image Alignment
Graduate School of AI, KAIST, South Korea.
GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
May 27, 2026Polytimi Anna Gkotsi, Andrii Zadaianchuk, Mohammad Mahdi DerakhshaniDiffusion Model Alignment 3D Asset Generation
University of Amsterdam, The Netherlands

Jul 7, 2026, cs.CVJ/K move · Enter open · S save

Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation

Sakuya Ota, Qing Yu, Kent Fujiwara, Satoshi Ikehata+1

Institute of Science Tokyo, Tokyo, Japan · LY Corporation, Tokyo, Japan · National Institute of Informatics (NII), Tokyo, Japan

Diffusion Model Alignment Text-to-Motion Generation Motion Diffusion Models Diffusion Models for Motion Generation Diffusion Models

Open paper AskPDF arXiv

Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temporal, especially in compositional and long-duration sequences that require semantic consistency across multiple action segments and smooth kinematic transitions throughout the trajectory. We posit that the initial noise is central to this consistency: within the Gaussian noise space, certain instances, i.e. winning noise tickets, carry latent structure that biases denoising toward particular motion semantics, even under null prompts. We propose WInning Noise Retrieval and Optimization (WINRO), a training-free, model-agnostic framework that improves text-motion alignment by selecting and refining such tickets before diffusion sampling. WINRO maps random noises to motion features generated under null prompts, retrieves the best-aligned noise for a given text, and refines it via a KL-regularized objective that reduces the residual semantic gap while preserving the Gaussian prior. An optional LoRA-based adapter amortizes this refinement into a single forward pass. WINRO consistently improves text-motion fidelity across different base models, MDM and MotionLCM, on HumanML3D without retraining, improves temporal robustness on the MTT benchmark, and generalizes to applications such as motion stylization and spatial constraint satisfaction.

Momentum

Related topics

Latest papers 131