Iterative Refinement

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 31

All topics

Few-Step Generation via Data-Space Iteration
Oct 8, 2026Shanchuan Lin, Yansong Peng, Fu-Yun Wang +1Iterative Refinement Flow-Based Generative Modeling
ByteDance Seed
Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning
Sep 20, 2026Alexander Christie, Miguel Moscoso, Alexei Novikov +2Sparse Recovery Dictionary Learning
Department of Mathematics, Stanford University, Stanford, CA 94305, USA · Department of Mathematics, Universidad Carlos III de Madrid, Leganés, Madrid 28911, Spain · Department of Mathematics, Pennsylvania State University, University Park, PA 16802, USA +1
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Sep 9, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +2Multi-Agent System Optimization LLM Agent Orchestration
AWS Generative AI Innovation Center
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation
Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText Generation Controllable Text Generation
University of Minnesota, Twin Cities
ODE-Based Transformer Decoders for Iterative Sign Language Translation
Aug 11, 2026Tuğçe Kızıltepe, Hacer Yalim KelesSign Language Translation Iterative Refinement
ASELSAN, Ankara, Türkiye · Department of Computer Engineering, Hacettepe University, Ankara, Türkiye
ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation
Jul 27, 2026Yuanjia Li, Tianyang Xu, Tao Zhou +3Video Object Segmentation Referring Video Object Segmentation
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China · Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK
Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames
Jul 22, 2026Boldsaikhan Bolorkhuu, Tsogtgerel GantumurReLU Neural Networks Iterative Refinement
2National University of Mongolia · 1McGill University · Institute of Mathematics and Digital Technology, Mongolian Academy of Sciences
Neural network realization of binary refinement iterates via a two-chart atlas selector
Jul 21, 2026Tsogtgerel GantumurReLU Neural Networks Neural Network Approximation Theory
McGill University, Montr´eal, QC, Canada · National University of Mongolia, Ulaanbaatar, Mongolia · Mongolian Academy of Sciences, Institute of Mathematics and Digital Technology
Countercurrent Multiplier Networks: A Renal-Inspired Iterative Operator with Provably Bounded Fixed-Point Dynamics
Jul 21, 2026Snigdha Chandan KhilarDynamical Systems Iterative Refinement
Independent Researcher
Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition
Jul 15, 2026Donghwan KimTable Structure Recognition LLM-as-a-Judge
Aidentyx Inc., San Jose, CA, USA
Interaction Scaling: Grounding the Third Axis of Test-Time Compute
Jul 13, 2026Bojie Li, Noah ShiTest-Time Scaling Automated Evaluation
Pine AI · University of Washington
RecRec: Recursive Refinement for Sequential Recommendation
Jul 12, 2026Pervez Shaik, Prosenjit Biswas, Abhinav Thorat +2Sequential Recommendation Iterative Refinement
Sony Research India India
Lightweight Polyp Segmentation via a Gain-Aware Prediction-Space Recursive Controller
Jul 3, 2026Jiachi Zhang, Zhuoyu Wu, Quanjun Wang +2Polyp Segmentation Medical Image Segmentation
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · South China University of Technology, Guangzhou, China · CyPhi(ΨΦ) AI Research Lab, School of IT, Monash University Malaysia +1
Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
Jun 28, 2026Alec Helbling, Andrey Bryutkin, Mauro Martino +3Structured Reasoning Flow-Based Generative Modeling
1Georgia Tech · 3MIT-IBM Computing Research Lab · 4IBM Research +1
Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models
Jun 15, 2026Yanming Zhang, Yihan Bian, Jingyuan Qi +3Masked Diffusion Models Diffusion Model Fine-Tuning
University of Maryland · Virginia Tech · Intuit +2
A fully GPU-based workflow for building physics emulators of hypersonic flows
Jun 11, 2026Fabian Paischer, Dylan Rubini, Deniz A. Bezgin +6Neural Surrogate Modeling Physics-Informed ML
ELLIS Unit, Institute for Machine Learning, JKU Linz · EMMI AI, Linz · Chair of Aerodynamics and Fluid Mechanics, TU Munich, Germany
Multi-Bitwidth Quantization for LLMs Using Additive Codebooks
Jun 11, 2026Liza Babaoglu, Shuangyi Chen, Ashish KhistiLLM Quantization Weight-Only Quantization
University of Toronto
A Turbo-Inference Strategy for Object Detection and Instance Segmentation
Jun 10, 2026Zhen Zhao, Gang Zhang, Xiaolin Hu +1Instance Segmentation Object Detection
School of Technology, Beijing Forestry University, Beijing 100091, China · Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China +1
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
Jun 9, 2026Junli Zha, Jinbo Wang, Chao Zhou +1LLM Decision-Making Iterative Refinement
SF Express
Tiny Recursive Models for Solving the J2-Perturbed Lambert Problem
May 30, 2026Minduli Wijayatunga, Roberto ArmellinDynamical Systems Trajectory Optimization
Department of Aerospace Engineering University of Illinois Urbana-Champaign Urbana-Champaign, IL, USA · Te Pūnaha Ātea – Space Institute University of Auckland Auckland, New Zealand
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
May 28, 2026Alessandro Burzio, Tobias Fischer, Sven Elflein +9Multi-View 3D Reconstruction Recurrent Transformers
NVIDIA · University of Modena and Reggio Emilia, AImageLab · ETH Zürich +1
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
May 21, 2026Xiaotian Liu, Shuyuan Shang, Xiaopeng Wang +2Neural PDE Solvers Spectral Bias
1Dartmouth College · 2CUHK Shenzhen · 3Lawrence Berkeley National Lab
One Pass Is Not Enough: Recursive Latent Refinement for Generative Models
May 14, 2026Mehdi Esmaeilzadeh, Alexia Jolicoeur-Martineau, Chirag Vashist +1Generative Modeling Image Generation Evaluation
1Simon Fraser University · 2Independent
Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
May 8, 2026Mingsong Yan, Dongyang Li, Charles Kulick +1Softmax Attention Transformer Interpretability
Department of Mathematics, University of California, Santa Barbara, CA
Alternating Target-Path Planning for Scalable Multi-Agent Coordination
May 8, 2026Yu Kumagai, Keisuke OkumuraMulti-Agent Coordination Multi-Robot Task Allocation
1Hitotsubashi University, Japan · 2National Institute of Advanced Industrial Science and Technology (AIST), Japan
Exact ReLU realization of tensor-product refinement iterates
May 5, 2026Tsogtgerel GantumurReLU Neural Networks Neural Network Approximation Theory
McGill University, Montréal, QC, Canada · National University of Mongolia, Ulaanbaatar, Mongolia · Mongolian Academy of Sciences, Institute of Mathematics and Digital Technology
Exact Loop Controllers for ReLU Realization of Homogeneous Curve Refinements
May 3, 2026Boldsaikhan Bolorkhuu, Tsogtgerel GantumurReLU Neural Networks Neural Network Approximation Theory
1McGill University · 2National University of Mongolia · Institute of Mathematics and Digital Technology, Mongolian Academy of Sciences
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
Apr 28, 2026Jiayi Guo, Linqing Wang, Jiangshan Wang +6Unified Multimodal Models T2I Generation
1Tsinghua University · 2Tencent HY
FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
Apr 18, 2026Yilong Dai, Yiming Sun, Yiheng Chen +3Flow Matching Neural PDE Solvers
University of Alabama · University of Pittsburgh
Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary CT Reconstruction: NAF Meets Diffusion Model
Nov 18, 2025Jiancheng Fang, Shaoyu Wang, Junlin Wang +3Diffusion Models for Image Restoration Sparse-View CT Reconstruction
School of Information Engineering, Nanchang University, Nanchang 330031, China

Oct 8, 2026, cs.LGJ/K move · Enter open · S save

Few-Step Generation via Data-Space Iteration

Shanchuan Lin, Yansong Peng, Fu-Yun Wang, Haoqi Fan

ByteDance Seed

Iterative Refinement Flow-Based Generative Modeling Flow Matching

Open paper AskPDF arXiv

Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires many network evaluations. Distillation can reduce this cost to one or a few evaluations; however, one-step generation often sacrifices quality, making few-step generation the practical operating regime. Existing few-step methods perform their iterative computation along the probability flow and therefore require a fixed, manually chosen timestep discretization. This discretization is often chosen heuristically and is expensive to tune; it may also be restrictive when refinement difficulty differs across samples or spatial locations. We introduce data-space iteration, a few-step generation framework that removes flow discretization altogether. Starting from noise, a shared generator directly refines its prediction in data space, with every iteration trained to produce the best sample permitted by its capacity. Our formulation integrates with distribution matching distillation (DMD) with minimal changes, enabling a controlled comparison between iteration methods under matched training settings. On class-conditional ImageNet 256x256, data-space iteration outperforms standard discretization baselines and matches or improves upon variants selected through schedule search, without requiring schedule-specific training. These results show that data-space iteration provides a simple and effective alternative to discretized flow-space iteration for fast generation.

Momentum

Related topics

Latest papers 31