Denoising Trajectory

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 41

All topics

Triangular Resampling for Long-Horizon Motion Generation
Sep 28, 2026Kunhang Li, Yiyi Cai, Xiangyue Zhang +5Denoising Trajectory Diffusion Models
The University of Tokyo · Alaya Lab · Japan Advanced Institute of Science and Technology
ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation
Sep 27, 2026Shizhe Liu, Jiayan Gu, Xiangyu Kong +1Facial Expression Recognition Residual Conditional Diffusion Model
Department of Computer Science, University of Oxford, Oxford, United Kingdom · School of Artificial Intelligence and Big Data, Hefei University, Hefei, China · Department of Computer Science, University of Exeter, Exeter, United Kingdom
Accelerating Video Diffusion via Training-Free Trajectory Routing
Sep 24, 2026Mustafa Munir, Huy Vu, Shreyas Misra +7Video Diffusion Models Denoising Trajectory
DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement
Sep 21, 2026Yixin Zheng, Jiangran Lyu, Yuntian Deng +6World Models Classical Planning
Institute of Automation, Chinese Academy of Sciences · Galbot · Peking University +2
GeomVLA: Unifying Scene, Motion, and Action in 3D
Sep 12, 2026Ziyin Xiong, Nikolaos Gkanatsios, Moritz Reuss +1Perception Pipeline Human Motion Prediction
Carnegie Mellon University · NVIDIA
Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models
Sep 9, 2026Yifan Yuan, Xiangyu Liu, Hongming Shan +5Text-To-Image Diffusion Models Diffusion Models
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Sep 3, 2026Byeongjun Park, Byung-Hoon Kim, Hyungjin ChungDenoising Trajectory Visual Fidelity
EverEx · Yonsei University · Korea University
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Aug 13, 2026Xichen Ye, Yifan Wu, Zhikang Xie +3Diffusion Models Denoising Trajectory
College of Computer Science and Artificial Intelligence, Fudan University · Faculty of Engineering, The Chinese University of Hong Kong · School of Data Science, Fudan University
FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations
Aug 9, 2026Yan Zeng, Changlu Guo, Oskar Kristoffersen +3Counterfactual Explanation Counterfactuals
Department of Applied Mathematics and Computer Science, Technical University of Denmark
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Aug 4, 2026Hoseong Tae, Jong-Seok LeeFlow-Matching Vision-Language-Action Diffusion-Based Vision-Language-Actions
School of Integrated Technology, Yonsei University
Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds
Aug 4, 2026Ning Zhu, An Chen, Mengfei Zhao +4Text-To-Image Diffusion Models Denoising Trajectory
Glasgow College, University of Electronic Science and Technology of China · School of Mathematical Sciences, University of Electronic Science and Technology of China
SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
Jul 23, 2026Wenbin Duan, Yan Shu, Zhuoyuan Fu +4Rectified Flow Diffusion Inversion
University of International Relations, Beijing, China · University of Trento, Trento, Italy · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China.
Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction
Jul 22, 2026Seonsoo Kim, Seongil Hong, Jun-Gill KangDiffusion Policies Denoising Trajectory
Agency for Defense Development
RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement
Jul 6, 2026Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao +2Text-To-Image Diffusion Models Denoising Trajectory
National Yang Ming Chiao Tung University, Hsinchu, Taiwan
When Does High-CFG Diffusion Inversion Fail? A Controlled Study of Prompt--Latent Interactions
Jul 6, 2026Yan Zeng, Yusuke Hosoya, Huyen T. T. Tran +1Diffusion Inversion Diffusion-Based Image Editing
GSIS Tohoku University Sendai, Japan · RIKEN AIP JAPAN
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Jun 21, 2026Merve Kocabas, Gege Gao, Bernhard Schölkopf +1Denoising Trajectory Generative Flow Networks
University of Tübingen, Tübingen, Germany · Max Planck Institute for Intelligent Systems, Tübingen, Germany · ETH Zürich, Zürich, Switzerland +2
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jun 19, 2026Jiaming He, Jiashu Zhang, Guanyu Hou +4Text-To-Video Generation Model Denoising Trajectory
Nanyang Technological University · Jilin University · The University of Manchester
Temporal Difference Learning for Diffusion Models
Jun 13, 2026Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu +1Denoising Trajectory Generative Models
Department of Engineering Science, University of Oxford, Oxford, United Kingdom · School of Computer Science, Carleton University, Ottawa, Canada.
Divide-and-Conquer Modeling for the CTF-4-Science Lorenz Benchmark
Jun 8, 2026Shundong LiChaos Denoising Trajectory
Worcester Polytechnic Institute Worcester, MA, USA
C $^3$ ache: Accelerating World Action Models with Cross Inference Chunk Cache
Jun 8, 2026Weisen Zhao, Lam Nguyen, Zhicong Lu +1Efficient World-Action Model Action Chunks
George Mason University · University of Central Florida
AsyncPatch Diffusion: spatially-flexible image generation
Jun 5, 2026Samuele Papa, Valentin De Bortoli, Guillaume Couairon +3Diffusion Models Denoising Trajectory
Google DeepMind · University of Amsterdam · The Netherlands Cancer Institute
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Jun 4, 2026Woojung Han, Seil Kang, Youngjun Jun +3Denoising Trajectory Diffusion Models
1Yonsei University, South Korea · 2NVIDIA, Taiwan.
Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models
Jun 3, 2026Anant Khandelwal, Manish GuptaLarge Language Model Reinforcement Learning Diffusion Language Models
Microsoft AI, India
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
May 29, 2026Ruotong Liao, Guowen Huang, Qing Cheng +6Interactive Video Generation Diffusion Transformers
Ludwig Maximilian University of Munich · MCML · Technical University of Munich +2
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
May 29, 2026Zekai Li, Ji Liu, Yiqing Huang +3Diffusion Language Models Constrained Decoding
Advanced Micro Devices, Inc. (AMD)
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
May 24, 2026Shuyuan Tu, Qi Tian, Zihan Yang +9Audio-Video Generation Denoising Trajectory
Fudan University · Tencent Hunyuan
Accelerating Rectified Flow Models via Trajectory-Aware Caching
May 16, 2026Xiao Liu, Kai Liu, Naiyang Guan +5Rectified Flow Denoising Trajectory
Shanghai Jiao Tong University, Shanghai, China · Academy of Military Science, Beijing, China · Huawei Technologies Ltd, Shenzhen, China
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
May 15, 2026Renye Yan, Jikang Cheng, Shikun Sun +7Diffusion-Based Reinforcement Learning Methods Reinforcement Fine-Tuning
1Peking University · 2Tsinghua University · 3Nanjing University +1
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
May 15, 2026Yan Luo, Ahmadou Aidara, Jingyi Lu +3Classifier-Free Guidance Diffusion-Based Image Editing
Harvard AI and Robotics Lab, Harvard University · School of Computing and Data Science, The University of Hong Kong · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University
DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
May 13, 2026Xianbing Sun, Jiahui Zhan, Liqing Zhang +1Virtual Try-On Denoising Trajectory
Shanghai Jiao Tong University
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
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
May 9, 2026Rohith Ramanan, A. N. Rajagopalan3D Generative Models High-Fidelity 3D Generation
Department of Physics Indian Institute of Technology Madras · Department of Electrical Engineering Indian Institute of Technology Madras
Normalizing Trajectory Models
May 8, 2026Jiatao Gu, Tianrong Chen, Ying Shen +3Denoising Trajectory Normalizing Flows
Apple · UIUC
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +4Diffusion-Based Reinforcement Learning Methods Diffusion Language Models
The Ohio State University · Apple
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
GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models
Apr 27, 2026Yiming Zhang, Sitong Liu, Ke Li +3Diffusion-Based Image Editing Diffusion Models
University of California San Diego, La Jolla, CA, USA · University of Washington, Seattle, WA, USA · Xidian University, Xi’an, China
Measuring Temporal Linguistic Emergence in Diffusion Language Models
Apr 25, 2026Harry LuDiffusion Language Models Large Language Model Uncertainty
School of Mathematics, University of Minnesota, Minneapolis MN, United States.
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
Apr 21, 2026Rui Li, Ke Hao, Yuanzhi Liang +4Denoising Trajectory Visual Generation
University of Science and Technology of China HeFei, China · Shanghai Jiao Tong University ShangHai, China · TeleAI ShangHai, China
LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
Mar 15, 2026Zengqun Zhao, Ziquan Liu, Yu Cao +5Video Diffusion Models Denoising Trajectory
Queen Mary University of London · Huawei R&D UK · Imperial College London
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Feb 6, 2026Yunze Tong, Mushui Liu, Canyu Zhao +7Generative Flow Networks Flow-Grpo
1Zhejiang University, Hangzhou, China · 2Taobao & Tmall Group of Alibaba, Hangzhou, China · 3Tsinghua University, Beijing, China
Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
Jun 25, 2025Shunqi Mao, Wei Guo, Chaoyi Zhang +3Diffusion Sampling Denoising Trajectory
School of Computer Science, The University of Sydney, Australia

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

Triangular Resampling for Long-Horizon Motion Generation

Kunhang Li, Yiyi Cai, Xiangyue Zhang, Fangyuan Tu+4

The University of Tokyo · Alaya Lab · Japan Advanced Institute of Science and Technology

Denoising Trajectory Diffusion Models Resampling Motion Generation Ground Truth

Open paper AskPDF arXiv

We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models. Built on FloodDiffusion's triangular denoising schedule, TR addresses the mismatch between ground-truth-derived training windows and model-generated inference states. Replacing only completed motion history leaves this mismatch unresolved in partially denoised states within the active window. TR therefore extends rollout-based training to these states, using ground-truth clamping to limit excessive drift. For each replayed sample, TR draws one denoising threshold, shared across latent positions and replay updates, and replays multi-step triangular denoising without gradient tracking. After each update, states below the threshold are replaced with noise-matched ground truth, while those at or above it retain model predictions. The resulting latent window enters the standard training update. This rollout construction supports both supervised training (TR) and distribution matching (TR-DMD). On 120-second motion generation from HumanML3D test prompts, TR and TR-DMD achieve state-of-the-art FID AUC within their respective non-DMD and DMD comparison groups. Supervised TR reduces FID AUC by 40.9% and FID degradation slope by 55.3% relative to matched post-training without replay.

Momentum

Related topics

Latest papers 41