Coarse-To-Fine

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

All topics

Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts
Sep 30, 2026Jingbo Wang, Wenxuan Song, Wenhao Yu +6Diffusion Transformers Action Expert
The Hong Kong University of Science and Technology (Guangzhou) · South China University of Technology · University of Science and Technology of China +3
Robust Multi-Model Fitting through Learning Neighbor Regions
Sep 14, 2026Chang Nie, Guangming Wang, Zhe Liu +1Multi--Task Learning Coarse-To-Fine
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China · Department of Engineering, Cambridge University, Cambridge CB2 1TN, UK
Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions
Sep 14, 2026Wenzhou Xia, Qiaoqiao Ding, Jingwei Liang +1Differentiable Optimal Transport Optimal Transport Approach
School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China · Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai 200240, China
BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
Sep 10, 2026Qianliang Wu, Haobo Jiang, Guangwei Gao +5Point Cloud Registration Image Registration
Nantong University · Nanyang Technological University · Nanjing University of Science and Technology +2
Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception
Sep 8, 2026Oleh Kolner, Thomas Ortner, Stanisław Woźniak +1Viewpoint-Dependent Active Perception Vision Foundation Models
IBM Research, Zurich, Switzerland · Graz University of Technology, Graz, Austria
Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline
Aug 9, 2026Dipit Saha, Shah Mohammad Abdul Mannan, Mohammad Raihan Rashid +2Accident Source Term Evaluation Code Accidents
Bangladesh University of Engineering and Technology
Semi-Dense Matching Uncertainty Is Not Just Local Confidence
Aug 9, 2026Khoa Hoang, Hoang-Tuan Nguyen, Huong Ninh +2Coarse-To-Fine Confidence Calibration
University of Engineering and Technology, Vietnam National University, Hanoi · Optoelectronics Center, Viettel Aerospace Institute, Viettel Group · National Yang Ming Chiao Tung University, Taiwan
GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs
Aug 4, 2026Zichuan Fu, Shirong Wang, Wenlin Zhang +10Graphical User Interface Coarse-To-Fine
City University of Hong Kong · Westlake University · Tencent Jarvis Lab
GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks
Jul 21, 2026Daniele Angioletti, Marco Nobile, Vittorio LimongelliGraph Neural Networks Large-Scale 3D Editing Dataset
Faculty of Biomedical Sciences, Euler Institute, Universit´a della Svizzera italiana, 6900 Lugano, Switzerland
Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
Jul 20, 2026Sangmin Han, Jinho Kim, Jinwoo Kim +2Visible Image Fusion Multi-Reference Image Generation
Yonsei University · AI Lab, CTO Division, LG Electronics
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
Jul 15, 2026Kai Chen, Ming Dai, Wenxuan Cheng +1Video Temporal Grounding Spatio-Temporal Attention
Southeast University
HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures
Jul 2, 2026Ziyun Qiao, Yue Min, Ruining Chen +1Pretraining Text Corpora
Wizard Quant, Beijing, China · University of Science and Technology of China, Hefei, China
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
Jun 25, 2026Xin Lin, Liang Zhang, Guoqi Ma +2Relation Extraction Relational Deep Learning
National Institute for Data Science in Health and Medicine, Xiamen University, China · School of Informatics, Xiamen University
Coarse-to-Fine: A Hybrid Self-Supervised Method for Non-rigid 3D Shape Matching
Jun 25, 2026Feifan Luo, Ting Li, Zhao Li +1Shape Correspondence Coarse-To-Fine
Zhejiang University, China · Zhejiang Lab, China · Wenzhou University of Technology, China
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Jun 5, 2026Jinhao Wu, Shiduo Zhang, Yicheng Liu +9Discrete Action Tokenizers Classical Planning
1Nanjing University · 2Shanghai Innovation Institute · 3Fudan University +1
CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors
Jun 4, 2026Shengxi Li, Zhaokun Hu, Ce Zheng +3Multi-Reference Image Generation Generative Models
Department of Electronic Information Engineering, Beihang University, Beijing 100191, China · School of Cyber Science and Technology, Beihang University, Beijing 100191, China · College of Electronic Science, National University of Defense Technology, Hunan 410073, China +1
TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
May 22, 2026Yifeng Di, Xuliang Huang, Tianyi ZhangCode Quality Coarse-To-Fine
Purdue University West Lafayette, IN · University of Illinois Urbana-Champaign Champaign, IL
Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control
May 14, 2026Nhat Le, Daochang Liu, Anh Nguyen +1Human Motion Generation Text-To-Motion Generation
The University of Western Australia, Crawley WA 6009, Australia · The University of Liverpool, Liverpool L69 3DR, United Kingdom
BRIDGE: Background Routing and Isolated Discrete Gating for Coarse-Mask Local Editing
May 8, 2026Peilin Xiong, Honghui Yuan, Junwen Chen +1Neural Mask Estimation Diffusion-Based Image Editing
Department of Informatics, The University of Electro-Communications, Tokyo, Japan
Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification
May 8, 2026Jungwoo Kim, Jun-Hyuk Kim, Jong-Seok LeeLearned Image Compression Neural Codecs
School of Integrated Technology, Yonsei University · BK21 Graduate Program in Intelligent Semiconductor Technology, Yonsei University · Department of Artificial Intelligence, Chung-Ang University
BAMI: Training-Free Bias Mitigation in GUI Grounding
May 7, 2026Borui Zhang, Bo Zhang, Bo Wang +6Graphical User Interface Graphical User Interface Agents
Tsinghua University, China · Lenovo Research, China
HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation
Apr 28, 2026Bingzi Zhang, Kaisi Guan, Ruihua SongHuman Motion Generation Video Quality
Gaoling School of Artificial Intelligence, Renmin University of China
Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System
Apr 27, 2026Yifei Wei, Linqing Zhong, Yi Liu +4Robotic Manipulation Action Space
1Beihang University · 2AgiBot
SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
Nov 25, 2025Da Li, Jiping Jin, Xuanlong Yu +6Skeleton Humanml3D
1Intellindust AI Lab · 3ShanghaiTech University · 5Didi Chuxing Co.Ltd +1

Sep 30, 2026, cs.ROJ/K move · Enter open · S save

Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts

Jingbo Wang, Wenxuan Song, Wenhao Yu, Han Zhao+5

The Hong Kong University of Science and Technology (Guangzhou) · South China University of Technology · University of Science and Technology of China+3

Diffusion Transformers Action Expert Geometric Guidance Coarse-To-Fine Iterative Denoising Methods

Open paper AskPDF arXiv

Efficient action generation in vision-language-action (VLA) models requires capturing both coarse action structure and fine-grained details. Discrete action tokens provide compact structural representations but sacrifice precision, while continuous action tokens offer high precision but often require multiple denoising steps. We introduce Discrete Forcing, a flow-matching framework that combines these representations through an explicit coarse-to-fine generation process. It first predicts discrete action tokens to establish a coarse action structure, then uses them to guide continuous action refinement. The discrete and continuous components share a common diffusion transformer backbone with specialized branches, maintaining a parameter count comparable to a conventional single-branch model while requiring only one forward pass per branch. Extensive evaluations across multiple benchmarks demonstrate improved performance and faster inference over a parameter-matched continuous action expert, with consistent performance gains as model capacity increases. Real-world experiments further demonstrate improvements on high-precision and dynamic manipulation tasks.

Momentum

Related topics

Latest papers 24