Consistency Distillation

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 16

All topics

RealtimeWAM: One-Step Asynchronous World Action Models
Oct 5, 2026Chengtao Lv, Jinyang Du, Shuyi Feng +7Efficient Inference for World Action Models Robotic Manipulation
Nanyang Technological University · Beihang University · Sensetime +1
Uncertainty-Aware Consistency Distillation for Few-Step Video Generation
Sep 30, 2026Lingyu Liu, Yaxiong Wang, Li Zhu +1Video Diffusion Models Few-Step Diffusion Sampling
School of Software Xi’an Jiaotong University Xi’an, China. · School of Computer and Information Science Hefei University of Technology Hefei, China. · Faculty of Science and Technology, and Institute of Collaborative Innovation University of Macau Macau, China.
FlowMap-OPD: Rollout--Kernel Separation for On-Policy Distillation of Few-Step Flow-Map Generators
Sep 29, 2026Zhiqi Li, Bo ZhuGenerative Flow Networks Flow Map Learning
Georgia Institute of Technology
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Sep 1, 2026Zinco J, Xunjie Zhu, Shen Huang +3Tool-Augmented Language Model Agents Consistency Distillation
Token Foundry, Alibaba Group
Stratified Consistency Distillation for Natural Language Formalization
Aug 31, 2026Zhichao Hou, Ferhat Erata, Joe Lilien +1LLM Fine-Tuning Consistency Distillation
North Carolina State University · Amazon Web Services
Multi-Mask Diffusion Language Models for Few-Step Generation
Jul 22, 2026Sijin Chen, Yinuo Ren, Heyang Zhao +3Masked Diffusion Models Diffusion Model Distillation
ByteDance Seed · Princeton University · Stanford University +2
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Jun 24, 2026Kaiwen Zheng, Guande He, Min Zhao +7Action-Conditioned Video Generation Autoregressive Diffusion
Tsinghua University · UT Austin · NVIDIA
Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation
Jun 23, 2026Baisen Wang, Chenxi Bao, Qisong HanText-to-Music Generation Controllable Music Generation
Work done in ZhuoLab. · DynamiX · Cardiff University
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Jun 21, 2026Songtao Tian, Guhan Chen, Bohan Li +2Curriculum RL Few-Step Diffusion Sampling
1Tsinghua University, Beijing, China · 2Huawei Large Model Data Technology Lab, Shenzhen, China
Flash-WAM: Modality-Aware Distillation for World Action Models
Jun 3, 2026Arman Akbari, Ci Zhang, Arash Akbari +6Video Diffusion Models Action-Conditioned World Models
1Northeastern University · University of Georgia · 3EmbodyX Inc.
Fast Image Super-Resolution via Consistency Rectified Flow
May 12, 2026Jiaqi Xu, Wenbo Li, Haoze Sun +8Rectified Flow Consistency Distillation
The Chinese University of Hong Kong · Huawei Noah’s Ark Lab · HKUST (GZ) +1
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
Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems
May 7, 2026Sicheng Ma, Tianyue Yang, Xiuzhe Wu +1Flow Matching One-Step Generative Modeling
Department of Physics University of Cambridge · The Center for Computational Science University College London · Department of Computer Science University College London
Alice v1: Distillation-Enhanced Video Generation Surpassing Closed-Source Models
Apr 27, 2026Wang Xiaoyu, Phong Nguyen, Chen ZhaoVideo Diffusion Models Diffusion Model Distillation
Mirage Team Open Source Research
On the Memorization of Consistency Distillation for Diffusion Models
Apr 26, 2026Bingqing Jiang, Difan ZouMemorization in Generative Models Consistency Distillation
School of Computing & Data Science, The University of Hong Kong. · School of Computing & Data Science and Institute of Data Science, The University of Hong Kong.
Dual-End Consistency Model
Feb 11, 2026Linwei Dong, Ruoyu Guo, Ge Bai +3One-Step Generative Modeling Consistency Distillation
1Zhejiang University · 2Bytedance Inc. · 3Zhejiang Lab

Oct 5, 2026, cs.CVJ/K move · Enter open · S save

RealtimeWAM: One-Step Asynchronous World Action Models

Chengtao Lv, Jinyang Du, Shuyi Feng, Yang Yong+6

Nanyang Technological University · Beihang University · Sensetime+1

Efficient Inference for World Action Models Robotic Manipulation Consistency Distillation World Action Models

Open paper AskPDF arXiv

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-expert iteration (\ie, multi-step action denoising) and inter-expert waiting (\ie, sequential execution of the video and action experts) still limit inference efficiency. To this end, we present RealtimeWAM, an extremely efficient WAM variant with one-step action generation and asynchronous inference, addressing these two bottlenecks. To reduce intra-expert iteration, we propose Teacher-Anchored Consistency Distillation (TACD) to address a local-global error gap: low local consistency error alone does not guarantee accurate final actions. TACD supplements local consistency with explicit supervision from the frozen teacher's multi-step rollout endpoint, enabling accurate one-step action generation. Additionally, we propose Cross-Expert Wavefront Pipelining (CEWP) to eliminate unnecessary expert-level waiting. It overlaps the two experts through block-wise sharing of the video KV cache, synchronizing only immediately before the corresponding action attention consumes it. Extensive experiments across diverse benchmarks (\eg, LIBERO, LIBERO-Plus and RoboTwin) and model variants (\eg, Fast-WAM and Faster-WAM) demonstrate the superiority of RealtimeWAM. Notably, RealtimeWAM maintains near-lossless performance (\ie,

<1\%

drop) across these benchmarks while delivering significant end-to-end speedup (\eg,

\sim25\times

on H100). Our code and checkpoints are available via this link.

Momentum

Related topics

Latest papers 16