Diffusion Alignment

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 65

All topics

iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
Oct 1, 2026Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel +2Diffusion Alignment Diversity
Pulchowk Campus, IOE, Tribhuvan University, Lalitpur, Nepal · INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria · NAAMII, Kathmandu, Nepal
Just Align $\bm{x}$ : Aligning Predictions, Not Representations
Sep 30, 2026Yuyao Zhang, Yuwei Hu, Ziyang Mai +1Diffusion Alignment Diffusion Models
Dartmouth College
WEIRDO: WEak resIdual Regularized DOob's h-transform diffusion alignment
Sep 30, 2026Denis SuchkovDiffusion Alignment Wasserstein Gradient Flows
HSE University, Russian Federation
Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment
Sep 30, 2026Jinho Chang, Jong Chul YeDiffusion Alignment Generative Models
Kim Jaechul Graduate School of AI KAIST Seoul, South Korea
Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models
Sep 30, 2026Shokichi Takakura, Akifumi Wachi, Rei Higuchi +2Diffusion Alignment Diffusion Models
LY Corporation · The University of Tokyo · RIKEN AIP
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
Sep 29, 2026Songlin Yang, Xiaotong Zhao, Jiacheng Zhang +5Diffusion-Based Reinforcement Learning Methods Diffusion Alignment
Tencent Video · The University of Hong Kong
What Visual Generators Need from Teachers: Rethinking Representation Alignment
Sep 28, 2026Yongcong Wang, Hingchin Chen, Mingyu Fan +6Diffusion Alignment Diffusion Transformers
Central South University · The Hong Kong University of Science and Technology · Tsinghua University +7
FestDPO: Few-step Generator Alignment with Direct Preference Optimization
Sep 28, 2026Jaewoo Lee, Kyuil Sim, Hyeongyu Kang +3Generative Models Diffusion Alignment
KAIST · MongooseAI · Omelet
Tilted Schrödinger Bridge Matching
Sep 28, 2026Sergei Kholkin, Evgeny Burnaev, Alexander KorotinSchrödinger Bridges Unpaired Image-To-Image Translation
Applied AI Institute
AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport
Sep 21, 2026Wuyi Liu, Xu Han, Yuren Chen +3Diffusion Alignment Iterative Denoising Methods
Huazhong University of Science and Technology · Beijing Jiaotong University · Beihang University +1
Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows
Sep 16, 2026Lennart Wittke, Vinicius AzevedoDiffusion Alignment Generative Flow Networks
ETH Zürich · Disney Research | Studios
DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
Sep 14, 2026Wenrui Xu, Anas Enanaa, Keshab K. ParhiSeizure Detection Representation Learning
University of Minnesota, Twin Cities
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
Sep 9, 2026Yansen Han, Shengyi Liao, Peng Sun +4Flow Models Preference Alignment
Westlake University · Zhejiang University · Kling Team, Kuaishou Technology
Latent Reward Registers for Diffusion Preference Alignment
Aug 4, 2026Yuanshen Guan, Zipeng Feng, Chengru Song +2Diffusion Alignment Reward Gradients
1Kling Team · University of Science and Technology of China
Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion
Jul 30, 2026Henglin Liu, Fangyuan Kong, Jing Wang +7Text-To-Video Diffusion Models Video Diffusion Models
Tsinghua University · Kling Team, Kuaishou Technology · Sun Yat-sen University
Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time
Jul 29, 2026Xinyi Wang, Yuyang Huang, Yalin Su +4Text-To-Image Diffusion Models Diffusion Alignment
Shanghai Jiao Tong University, Shanghai, China
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Jul 20, 2026Shigui Li, Delu ZengDiffusion Alignment Diffusion Models
School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis
Jul 19, 2026Lingwei Dang, Juntong Li, Zonghan Li +5Hand-Object Interaction Detection 3D Motion
South China University of Technology, Guangzhou, China · Beijing Normal University, Beijing, China · Tsinghua University, Beijing, China +1
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Jul 15, 2026Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1Diffusion Models Diffusion Alignment
University of British Columbia · Inverted AI · Alberta Machine Intelligence Institute
Efficient bias mitigation in T2I diffusion models using Concept Graphs
Jul 3, 2026Mansi, Avinash Kori, Francesco LeofanteText-To-Image Diffusion Models Diffusion Alignment
Department of Computing Imperial College London
Open-Weather Robust 3D Detection via Dual-Critic Diffusion Alignment
Jul 2, 2026Shuyao Li, Chuanxing Geng, Heyang Sun +23D Object Detection Autonomous Driving Perception
Nanjing University of Aeronautics and Astronautics, Nanjing, China · MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China
PAPA: Online Personalized Active Preference Alignment
Jul 1, 2026Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas +2Preference Alignment Diffusion Alignment
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 +2Text-To-Image Diffusion Models Text-To-Image
Institute of Artificial Intelligence University of Central Florida, Orlando, United States
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Jun 28, 2026Chen Wang, Peiran Yun, Pan Xie +1Diffusion Alignment Distribution Matching Distillation
Department of Statistics and Data Science, Tsinghua University · Department of Computer Science and Technology, Tsinghua University · Bytedance Inc
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Jun 23, 2026Haorui Ji, Weizhe Liu, Hongdong Li +13D Gaussian 3D Generative Models
The Australian National University · ByteDance
PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models
Jun 22, 2026Ruolan Sun, Pawel PolakDiffusion Alignment Contrastive Flow Matching
Stony Brook University
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Jun 17, 2026Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4Contrastive Flow Matching Diffusion Alignment
FAIR at Meta · Columbia University · Mila – Québec AI Institute +3
MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training
Jun 7, 2026Lianyu Pang, Tianlin Pan, Cheng Da +5Diffusion Alignment Diffusion Transformers
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 +7Text-To-Image Diffusion Alignment
Tsinghua University · University of British Columbia · Vector Institute +2
Drifting Preference Optimization for One-Step Generative Models
Jun 1, 2026Zhou Jiang, Yandong Wen, Zhen LiuDiffusion Alignment Few-Step Generation
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 +3Medical Image Generation Diffusion Alignment
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
Improving Visual Representation Alignment Generation with GRPO
May 30, 2026Shentong Mo, Sukmin YunDiffusion Alignment Diffusion Transformers
Carnegie Mellon University · Hanyang University
Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
May 28, 2026Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon +1Text-To-Image Diffusion Models Diffusion Alignment
Graduate School of AI, KAIST, South Korea.
Explicit Critic Guidance for Aligning Diffusion Models
May 26, 2026Zhengyang Liang, Qihang Zhang, Ceyuan YangDiffusion Alignment Diffusion-Based Reinforcement Learning Methods
University of Toronto · Vector Institute · The Chinese University of Hong Kong
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
May 26, 2026Austin Wang, Jiaqi Han, Stefano Ermon +1Diffusion Alignment Text-To-Image Diffusion Models
Caltech · Stanford University
DRM: Diffusion-based Reward Model With Step-wise Guidance
May 25, 2026Jaxon Zhang, Binxin Yang, Hubery Yin +2Diffusion Alignment Diffusion Models
Peking University · Work done during an internship at WeChat Vision, Tencent Inc. · WeChat Vision, Tencent Inc.
Inference-Time Alignment of Diffusion Models via Trust-Region Iterative Twisted Sequential Monte Carlo
May 24, 2026Weixin Wang, Yu Yang, Wei Deng +1Diffusion Alignment Diffusion Models
Duke University · Morgan Stanley
When Preference Labels Fall Short: Aligning Diffusion Models from Real Data
May 19, 2026Weiyan Chen, Weijian Deng, Yao Xiao +5Diffusion Alignment Preference Alignment
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Australian National University, Canberra, Australia +2
Stitched Value Model for Diffusion Alignment
May 19, 2026Hyojun Go, Hyungjin Chung, Prune Truong +8Diffusion Alignment Diffusion Models
1ETH Zurich · 2Google · University of Copenhagen
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
May 16, 2026Shaodong Xu, Zhendong Wang, Litong Gong +4Diffusion Alignment Diffusion Transformers
University of Science and Technology of China
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
May 15, 2026Xiaoxuan He, Siming Fu, Zeyue Xue +9Video Diffusion Models Diffusion Alignment
Zhejiang University · Joy Future Academy · Independent Researcher +1
CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis
May 12, 2026Yunsung Chung, Alex El Darzi, Carlo El Khoury +3Medical Image Generation Diffusion Alignment
Department of Computer Science, Tulane University, New Orleans, LA 70118 · School of Medicine, Tulane University, New Orleans, LA 70112
The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives
May 12, 2026Ankur Moitra, Andrej Risteski, Dhruv RohatgiDiffusion Alignment Reward Gradients
Gradient-Free Noise Optimization for Reward Alignment in Generative Models
May 12, 2026Jeongsol Kim, Hongeun Kim, Jian Wang +1Reward Gradients Diffusion Alignment
KAIST AI1 · Snap Inc.2
Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
May 10, 2026Yunhong Lu, Qichao Wang, Hengyuan Cao +2Rectified Flow Diffusion Alignment
Zhejiang University · Shanghai Institute for Advanced Study-Zhejiang University · Shanghai Institute for Mathematics and Interdisciplinary Sciences
DiffATS: Diffusion in Aligned Tensor Space
May 10, 2026Jinhua Lyu, Tianmin Yu, Brian Kim +3Diffusion Alignment Diffusion Models
Northwestern University
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
May 9, 2026Jiaming Li, Chenyu Zhu, Nanxi Yi +9Diffusion Alignment Diffusion-Based Reinforcement Learning Methods
1MAIR Lab, Huazhong University of Science and Technology · 2Kuaishou Technology · 3Nanyang Technological University +2
Flow-OPD: On-Policy Distillation for Flow Matching Models
May 8, 2026Zhen Fang, Wenxuan Huang, Yu Zeng +8Text-To-Image Diffusion Models Image-Text Alignment
University of Science and Technology of China · University of California, Los Angeles · 3The Chinese University of Hong Kong +1
Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
May 8, 2026Jingyuan Zhu, Biaolong Chen, Le Zhang +3Diffusion Alignment Video Diffusion Models
Alibaba Group
Inference-Time Attribute Distribution Alignment for Unconditional Diffusion
May 8, 2026Hao Luan, See-Kiong Ng, Chun Kai LingDiffusion Alignment Diffusion Models
School of Computing, National University of Singapore · Institute of Data Science, National University of Singapore
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
May 8, 2026Shih-Yu Lai, Hirozumi Yamaguchi, Shang-Tse Chen +2Federated Learning Multimodal Fusion
National Taiwan University · RIKEN-CCS · The University of Osaka +1
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
May 8, 2026Zhenhan Fang, Aixin Tan, Jian HuangOnline Conformal Prediction Nonconformity Scores
Department of Statistics and Actuarial Science University of Iowa Iowa, IA 52242, USA · Departments of Data Science and AI, and Applied Mathematics The Hong Kong Polytechnic University Hong Kong, China
MARBLE: Multi-Aspect Reward Balance for Diffusion RL
May 7, 2026Canyu Zhao, Hao Chen, Yunze Tong +3Diffusion-Based Reinforcement Learning Methods Diffusion Alignment
Zhejiang University · Work done during an internship at HiThink. · HiThink +1
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
May 6, 2026Jiaming Hu, Jiamu Bai, Haoyu Wang +2Diffusion Alignment Preference Alignment
Boston University · Penn State University · University at Albany
AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
May 5, 2026Ruibin Min, Yexin Liu, Aimin Pan +5Diffusion Alignment Diffusion Transformers
Sun Yat-sen University · The Hong Kong University of Science and Technology · VNET Group +2
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
Apr 27, 2026Xinxin Liu, Ming Li, Zonglin Lyu +2Backtranslation Augmented Direct Preference Optimization Diffusion Alignment
University of Central Florida
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Apr 26, 2026Haosen Li, Wenshuo Chen, Lei Wang +3Diffusion Alignment Text-To-Image Diffusion Models
1The Hong Kong University of Science and Technology (Guangzhou) · 2Griffith University & Data61/CSIRO
Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
Apr 23, 2026Luis Barba, Johannes Kirschner, Benjamin BejarCone-Beam Computed Tomography Sparse-View
Swiss Data Science Center (SDSC) in Paul Scherrer Institute (PSI), Villigen, Switzerland. · Swiss Data Science Center (SDSC) and ETH Zurich, Switzerland. · Swiss Data Science Center (SDSC) and Paul Scherrer Institute (PSI), Villigen, Switzerland.
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
Apr 19, 2026Jeongjae Lee, Jinho Chang, Jeongsol Kim +1Diffusion Alignment Diffusion Models
Graduate School of AI KAIST, Korea
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Mar 18, 2026Xi Ye, Wenjia Yang, Yangyang Xu +4Video Diffusion Models Diffusion Alignment
Tsinghua University · Ant Group · University of Chinese Academy of Sciences

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

iADD: Improving Alignment and Diversity in Diffusion Policy Optimization

Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel, Ajad Chhatkuli+1

Pulchowk Campus, IOE, Tribhuvan University, Lalitpur, Nepal · INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria · NAAMII, Kathmandu, Nepal

Diffusion Alignment Diversity Reward Functions

Open paper AskPDF arXiv

Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward function. However, current approaches to reward optimizations do so at the cost of diversity and quality. In this paper, we provide better tradeoffs through careful theoretical considerations and method design. We analyze the theoretical framework and mathematically demonstrate that \emph{only-latter timestep} updates of diffusion model may be harmful for diversity contrary to the conclusions presented in a previous work. Additionally, we propose an incremental Feynman-Kac training based on strong theoretical foundations in order to achieve the best-yet alignment-diversity tradeoffs. We perform extensive experiments and compare our method against related diffusion policy optimization approaches in three different tasks and also provide strong ablations for each component, thus validating strong performance gains in both alignment and diversity.

Momentum

Related topics

Latest papers 65