Consistency Models

Follow this topic Ask about this topic

Consistency Models learn to produce the same clean output from different noise levels along a diffusion trajectory, making generation possible in one or a few evaluations instead of many iterative denoising steps. They are trained either by distilling a pretrained diffusion model’s probability-flow trajectory or directly with consistency objectives, sometimes combined with flow matching. Work applies them to image generation and tasks such as super-resolution, MRI reconstruction, video prediction, and 3D generation, often adding measurement or structural constraints. The central challenge is preserving quality, fidelity, and diversity as sampling gets faster, while controlling training instability and errors that can accumulate across trajectory steps.

Latest papers

25 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension
Oct 26, 2026Vinay Saji Mathew, Soundar R. Kumara, Gretta D Kellogg +1Consistency Models Consistency Distillation
The Pennsylvania State University · State University of New York at Buffalo
Iterating Consistency Models: Stability, Error Bounds and Noise Schedules
Oct 2, 2026Alessio Spagnoletti, Abdul-Lateef Haji-Ali, Andrés Almansa +3Consistency Models Few-Step Diffusion Sampling
Laboratoire MAP5, UMR 8145, Université Paris Cité, CNRS · Heriot-Watt University, School of Mathematical and Computer Sciences & Maxwell Institute for Mathematical Sciences · École Polytechnique +1
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
Aug 20, 2026Merve Gülle, Junno Yun, Yaşar Utku Alçalar +1Accelerated MRI Reconstruction Diffusion-Based Inverse Problems
Department of Electrical and Computer Engineering, University of Minnesota, MN, USA · Center for Magnetic Resonance Research, University of Minnesota, MN, USA
MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories
Aug 17, 2026Lauri Lovén, Jaakko Sauvola, Jukka Riekki +1LLM Agent Memory Graph-Based Agent Memory
Future Computing Group, University of Oulu, Finland · University of Oulu, Finland · University of Helsinki and University of Oulu, Finland
Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation
Jul 11, 2026Ryan GillespieByzantine-Robust Federated Learning Algorithmic Accountability
Independent researcher
StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
Jul 7, 2026Sergey Volkov, Yang Li, Ye LuoAgent Memory Multi-Agent Systems
The University of Hong Kong
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
Jun 15, 2026Sajjad KhanMulti-Agent LLM Systems Formal Verification
independent researcher
Leveraging Structural Constraints for Diffusion-based Neural TSP Solvers
Jun 8, 2026Mickaël Basson, Philippe PreuxTraveling Salesperson Problem Inference-Time Optimization
CRIStAL, Scool · Université de Lille, France · CNRS, France +2
TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory
Jun 4, 2026Ziming WangKnowledge Conflicts in Language Models LLM Agent Memory
The Hong Kong University of Science and Technology Hong Kong, Hong Kong SAR
DCFold: Efficient Protein Structure Generation with Single Forward Pass
May 18, 2026Zhe Zhang, Yuanning Feng, Yuxuan Song +3Protein Structure Prediction Protein Structure Generation
Institute for AI Industry Research (AIR), Tsinghua University · Department of Computer Science and Technology, Tsinghua University · School of Computer Science and Technology, Huazhong University of Science and Technology +1
S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
May 16, 2026Sajjad KhanMulti-Agent LLM Systems Consistency Models
Conflict-Free Replicated Data Types for Neural Network Model Merging: A Two-Layer Architecture Enabling CRDT-Compliant Model Merging Across 26 Strategies
May 16, 2026Ryan GillespieModel Merging Consistency Models
Independent researcher
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
May 14, 2026Yanzuo Lu, Ronglai Zuo, Jiankang DengRL for Diffusion Models Long-Horizon Video Generation
Imperial College London
ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction
May 9, 2026Alen Mrdovic, Qingze, Liu +6Trajectory Generation Multi-Agent Trajectory Prediction
Tony · Rutgers University, New Brunswick · The College of New Jersey
GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model
May 7, 2026Shaozhen Ma, Wei Huang, Hanchen Wang +2Conditional Generative Modeling Consistency Models
University of New South Wales · University of Technology Sydney
Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
May 6, 2026Pranav A, Shashank B, Pranav Siddappa +3Point Cloud Anomaly Detection Industrial Anomaly Detection
1R.V. College of Engineering · 2Technical University of Applied Sciences Würzburg-Schweinfurt
Inconsistent Databases and Argumentation Frameworks with Collective Attacks
May 5, 2026Yasir Mahmood, Jonni Virtema, Timon Barlag +1Computational Argumentation Relational Databases
Data Science Group, Heinz Nixdorf Institute, Paderborn University, Germany · School of Computing Science, University of Glasgow, United Kingdom · School of Computer Science, University of Sheffield, United Kingdom +1
ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
May 4, 2026Aoyu Liu, Zhen Liu, Ziyi Wang +3Image Enhancement HDR Imaging
University of Electronic Science and Technology of China
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
Apr 10, 2026Chia-Hong Hsu, Randall BalestrieroConsistency Models Diffusion Model Guidance
Brown University
The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation
Mar 10, 2026Vladyslav ParakhinAccess Control Tool Access Control for LLM Agents
Senior Data Engineer, Okta
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution
Feb 27, 2026Chengyan Deng, Zhangquan Chen, Li Yu +3Image Super-Resolution Consistency Models
University of Electronic Science and Technology of China · Tsinghua University · Nanjing University
Dual-End Consistency Model
Feb 11, 2026Linwei Dong, Ruoyu Guo, Ge Bai +3One-Step Generative Modeling Consistency Distillation
1Zhejiang University · 2Bytedance Inc. · 3Zhejiang Lab
Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training
Feb 10, 2026Che-Chia Chang, Chen-Yang Dai, Te-Sheng Lin +2Physics-Informed Generative Modeling PDE Surrogate Modeling
Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Hsinchu, Taiwan · Department of Applied Mathematics National Yang Ming Chiao Tung University Hsinchu, Taiwan · Department of Applied Mathematics National Yang Ming Chiao Tung University Hsinchu, Taiwan National Center for Theoretical Sciences National Taiwan University Taipei, Taiwan
MACS: Measurement-Aware Consistency Sampling for Inverse Problems
Oct 2, 2025Amirreza Tanevardi, Pooria Abbas Rad Moghadam, Seyed Mohammad Eshtehardian +2Diffusion Model Sampling Inverse Problems
Department of Electrical Engineering Sharif University of Technology Tehran, Iran · Electronics Research Institute Sharif University of Technology Tehran, Iran
A binarized-domains arc-consistency algorithm for TCSPs: its computational analysis and its use as a filtering procedure in solution search algorithms
Feb 22, 2020Amar IsliConstraint Satisfaction Temporal Consistency
University of Sciences and Technology Houari Boumedi`ene · Faculty of Computer Science · Department of Artiﬁcial Intelligence and Data Science +2

Oct 26, 2026J/K move · Enter open · S save

Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension

Vinay Saji Mathew, Soundar R. Kumara, Gretta D Kellogg, William KM Lai

The Pennsylvania State University · State University of New York at Buffalo

Consistency Models Consistency Distillation Diffusion Model Distillation

Open paper AskPDF arXiv

Continuous-time consistency models are an attractive route to few-step generation. They remove the discretization error inherent to the timestep grid that discrete-time consistency models depend on. Until recently, however, training them was unstable. Lu & Song (2025) address this with the TrigFlow formulation and a coordinated set of architectural and training-objective changes. We conduct an independent empirical study of this framework on CIFAR-10 and ImageNet-64. No open-weight TrigFlow teachers exist at these scales, so we train them from scratch and then verify the consistency distillation (sCD) and consistency training (sCT) behavior of students initialized from these teachers. On CIFAR-10, our students reproduce the reported FID at one and two steps. On ImageNet-64, they fall short, a gap that appears related to our teacher and to architectural choices the paper leaves unspecified. We also report a parameter-count gap of about 5% between the model size stated in the paper and a faithful re-implementation, which we attribute to the scale-and-shift conditioning projections in Adaptive Double Normalization. We then propose Multistep sCD (MS-sCD), a continuous-time, segment-conditioned multistep generalization of sCD. The segment-conditioning idea is borrowed from the discrete-time multistep consistency distillation of Heek et al. (2024); we build on their preliminary continuous-time experiments within the TrigFlow/sCM framework. The rest of the algorithm follows sCD. MS-sCD replaces sCM's two-step intermediate time with a fixed segment-boundary schedule and recovers sCD at M = 1. We report FID at M = 2, 4, 8 and compare against the discrete-time MSCD baseline. Code, model weights, and training scripts are available on GitHub (Mathew et al., 2026).