Diffusion Model Guidance

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 75% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 234

All topics

Are we really tilting? The mechanics of reward guidance in flow and diffusion models
Jun 1, 2026Sanjit Dandapanthula, Nicholas M. BoffiReward Hacking Diffusion Model Guidance
Carnegie Mellon University
Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
Jun 1, 2026Yuheng Chen, Teng Hu, Yuji Wang +3Diffusion Model Guidance Video Diffusion Models
Shanghai Jiao Tong University Shanghai, Shanghai, China · University of Electronic Science and Technology of China Chengdu, Sichuan, China · Zhejiang University Hangzhou, Zhejiang, China
NDPP-Grasp: Non-Differentiable Physical Plausibility Constraint-Guided Task-Oriented Dexterous Grasp Generation
Jun 1, 2026Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani +1Diffusion Model Guidance Robotic Grasping
Lancaster University UK
Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization
Jun 1, 2026Liyuan Ma, Xueji Fang, Guo-Jun QiDiffusion Model Guidance Subject-Driven Image Generation
Westlake University · Hangzhou, China · Zhejiang University
Training-Free Imitation Learning with Closed-Form Diffusion Policies
May 31, 2026Raghav Mishra, Ian R. ManchesterDiffusion Model Guidance Visuomotor Policy Learning
Australian Center for Robotics, ARIAM Hub, and School of Aerospace, Mechanical and Mechatronic Engineering University of Sydney
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
May 29, 2026Shreyansh Modi, Akshat Tomar, Aarush AggarwalDiffusion Model Guidance Image Enhancement
Indian Institute of Technology Roorkee
DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
May 28, 2026Hidir Yesiltepe, Koutilya PNVR, Gaurav Pathak +4Diffusion Model Guidance Video Diffusion Models
1Virginia Tech · 2Adobe
GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
May 28, 2026Yuqing Chen, Lin Liu, Haisu Wu +4Diffusion Model Guidance Video Diffusion Models
Tsinghua University, China · Huawei, China · Southeast University, China +2
Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion Control
May 28, 2026Hao Ren, Zetong Bi, Yiming Zeng +5Diffusion Model Guidance Diffusion-Based Planning
Sun Yat-sen University, Guangzhou, China · Insta360 Research, Shenzhen, China
Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation
May 28, 2026Jungmin Ko, Jungwon Park, Jimyeong Kim +3Diffusion Model Guidance T2I Generation
Interdisciplinary Program in Artificial Intelligence, Seoul National University · Research Institute for Convergence Science, Seoul National University · Daegu Gyeongbuk Institute of Science and Technology +3
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
May 27, 2026Zhuohan Liu, Wujian Peng, Yitong Chen +1Diffusion Model Guidance Direct Preference Optimization
Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University · Shanghai Collaborative Innovation Center of Intelligent Visual Computing
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
May 27, 2026Gabriel Moreira, Manuel Marques, João Paulo Costeira +1Diffusion Model Guidance Diffusion Guidance
Institute for Systems and Robotics, Instituto Superior Técnico, Lisbon, Portugal · Carnegie Mellon University, Pittsburgh, PA, USA
DebFilter: Eradicating Biases Stashed in Value
May 27, 2026Seung Hyuk Lee, Songkuk KimDiffusion Model Guidance Cross-Attention
School of Integrated Technology, BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University
Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales
May 27, 2026Myeongsoo Kim, Eunji Kim, Minwoo Chae +1Diffusion Model Guidance Classifier-Free Guidance
1POSTECH · 2Amazon
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
May 27, 2026Junlin WangDiffusion Model Guidance Diffusion Guidance
School of Engineering and Applied Science University of Pennsylvania
Explicit Critic Guidance for Aligning Diffusion Models
May 26, 2026Zhengyang Liang, Qihang Zhang, Ceyuan YangDiffusion Model Alignment Diffusion Model Guidance
University of Toronto · Vector Institute · The Chinese University of Hong Kong
Scheduled Style Injection: Expanding the Style-Content Pareto Frontier in Training-Free Diffusion-based Style Transfer
May 26, 2026Amey Sunil KulkarniDiffusion Model Guidance Image Style Transfer
Independent Researcher
Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
May 26, 2026Junseo Bang, Dong Ju Mun, Hoigi Seo +2Diffusion Model Guidance Diffusion Timestep Scheduling
Dept. of Electrical and Computer Engineering · INMC · IPAI & AIIS
Co-folding model guided by structural proteomics
May 25, 2026Alon Shtrikman, Nitzan Simchi, Michal Ran Shchory +3Diffusion Model Guidance Protein Structure Prediction
1Protai Bio
OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
May 25, 2026Zitong Xiao, Yuda Qiu, Zisheng Ye +1Diffusion Model Guidance Image Editing
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · Guangdong Provincial Key Laboratory of Future Networks of Intelligence · FNii-Shenzhen
DRM: Diffusion-based Reward Model With Step-wise Guidance
May 25, 2026Jaxon Zhang, Binxin Yang, Hubery Yin +2Diffusion Model Alignment Diffusion Model Guidance
Peking University · Work done during an internship at WeChat Vision, Tencent Inc. · WeChat Vision, Tencent Inc.
Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference
May 24, 2026Agata Żywot, Iason Skylitsis, Thijmen Nijdam +4Diffusion Model Guidance Test-Time Optimization
University of Amsterdam, Netherlands
D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
May 24, 2026Wenjie Zheng, Haoji Hu, Jiali Lu +2Diffusion Model Guidance Dataset Distillation
Zhejiang University, China
Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning
May 24, 2026Yu Yang, Yihong Guo, Anqi Liu +1Diffusion Model Guidance Reinforcement Learning
Duke University · Johns Hopkins University
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
May 23, 2026Sol Park, Soobin UmDiffusion Model Guidance Diffusion Sampling
Agency for Defense Development, Daejeon, South Korea · Department of Artificial Intelligence, Kookmin University, Seoul, South Korea.
Representation-Guided Discrete Molecular Graph Retrosynthesis
May 23, 2026Jiahai Huang, Anjie Qiao, Zhen Wang +2Diffusion Model Guidance Molecular Graph Generation
Sun Yat-sen University Guangzhou, China · University of Science and Technology of China Hefei, China
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
May 22, 2026Bo Jiang, Depu Meng, Yihan Hu +3Physical Consistency in Video Generation Diffusion Model Guidance
Applied Intuition · University of California, Berkeley
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
May 21, 2026Javad Rajabi, Kimia Shaban, Koorosh Roohi +2Rotary Positional Embeddings Diffusion Model Guidance
University of Toronto · Vector Institute
Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
May 21, 2026Henry Che, Jingkang Wang, Yun Chen +33D Gaussian Splatting Diffusion Model Guidance
1Waabi · University of Illinois Urbana-Champaign · University of Toronto
Hierarchical Variational Policies for Reward-Guided Diffusion
May 20, 2026Kushagra Pandey, Farrin Marouf Sofian, Jan Niklas Groeneveld +2Diffusion Models for Image Restoration Diffusion Model Guidance
Department of Computer Science University of California Irvine

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

Are we really tilting? The mechanics of reward guidance in flow and diffusion models

Sanjit Dandapanthula, Nicholas M. Boffi

Carnegie Mellon University

Reward Hacking Diffusion Model Guidance Doob H-Transform

Open paper AskPDF arXiv

Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hacking: the guided model over-optimizes the reward at the cost of fidelity to the learned distribution. Prior work has attributed this to the complexity of neural reward functions or implicit biases in diffusion training, but its fundamental origins remain poorly understood. We show that reward hacking arises from an approximation made in most practical implementations of reward-guided diffusion -- finite-particle plug-in estimation of the Doob h-function -- even in the simplest non-trivial settings of Gaussian and Gaussian mixture targets with quadratic rewards. In closed form, we isolate two distinct failure modes of the plug-in estimator: it leads to reward hacking within each mode and it cannot select high-reward modes. We propose a closed-form reward damping schedule that corrects the within-mode bias with no additional compute, and clarify the role of best-of-n sampling in compensating for the mode selection failure. Experiments on Gaussian mixture targets, a 2D checkerboard, and FLUX.1 text-to-image generation confirm that our theoretical insights carry over to practical settings.

Momentum

Related topics

Latest papers 234