Action Generation

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 180% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 112

All topics

Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation
Jun 16, 2026Tianyu Wang, Ying Wang, Zhihao Liu +2Attractors Latent Variable
Department of Production Engineering, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden
Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies
Jun 16, 2026Meipo Dai, Qiyuan Zhuang, He-Yang Xu +4Robot Policies Action Generation
Southeast University · The Chinese University of Hong Kong
PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
Jun 15, 2026Yanan Zhou, Ranpeng Qiu, Yincong Chen +2Robotic Manipulation Robot Systems
School of Computer Science, The University of Sydney. · Australian Centre For Robotics, The University of Sydney.
Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models
Jun 12, 2026Ge Wang, Xinyu Tan, Xiang Li +11Latent Actions Offline Reinforcement Learning
Ising AI · CUHK-Shenzhen · PKU
ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation
Jun 12, 2026Yanzhao Guo, Wenkai Chen, Jianwei ZhangDiffusion-Based Vision-Language-Actions Action Generation
Shanghai Jiao Tong University · Technical Aspects of Multimodal Systems (TAMS), Department of Informatics, Universität Hamburg
Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing
Jun 12, 2026Duc Minh Nguyen, Bao-Ngoc Dao, Tung M. Luu +15Generalizable Vision-Language-Action Policies Diffusion-Based Vision-Language-Actions
Center for AI Research, VinUniversity · VinRobotics · KAIST +8
GeoHAT: Geometry-Adaptive Hybrid Action Transformer for Mobile Manipulation
Jun 11, 2026Xiangyu Zhu, Renjun Wu, Luzhou Ge +2Action Generation Geogs-Slam
Beijing Institute of Technology
DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model
Jun 10, 2026Pankhuri Vanjani, Zhuoyue Li, Jakub Suliga +4Diffusion-Based Vision-Language-Actions Action Generation
Intuitive Robots Lab, Karlsruhe Institute of Technology (KIT), Germany · NVIDIA · Robotics Institute of Germany
Dynamic Execution Horizon Prediction for Chunk-based Robot Policies
Jun 9, 2026Yuchi Zhao, Miroslav Bogdanovic, Arjun Sohal +5Action Chunks Long-Horizon Manipulation
Department of Computer Science, University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON M5G 0C6, Canada · Acceleration Consortium, 700 University Ave., Toronto, ON M7A 2S4, Canada +7
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
Jun 9, 2026Thanh Nguyen, Tri Ton, Hongbin Choe +2Diffusion-Based Reinforcement Learning Methods Flow Policies
Department of Electrical Engineering, KAIST, Daejeon, Korea.
Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
Jun 9, 2026Zi Yin, Peilin Chai, Siyuan Huang +1Diffusion Policies Visuomotor Policy
Tsinghua University · Independent Researcher · Johns Hopkins University +1
ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies
Jun 7, 2026Bingjia Huang, Xiangyu Li, Xiang Wang +7Robot Policies Action Generation
Institute for AI Industry Research (AIR), Tsinghua University · University of Electronic Science and Technology of China · Work done during internship at AIR, Tsinghua University. +1
Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Jun 6, 2026Ziang Li, Dongzhou Cheng, Yibin Wang +5Efficient World-Action Model Action Prediction
Wuhan University · Shanghai Innovation Institute · Southeast University +2
TBD-VLA: Temporal Block Diffusion Vision Language Action Model
Jun 5, 2026Sung-Wook Lee, Xuhui Kang, Yen-Ling KuoDiffusion-Based Vision-Language-Actions Action Generation
University of Virginia
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
Jun 4, 2026Qize Yu, Jiadi You, Yuran Wang +10Robotic Manipulation Affordances
Peking University · Hong Kong University of Science and Technology (Guangzhou) · The Chinese University of Hong Kong +1
Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
Jun 4, 2026Yitong Chen, Shiduo Zhang, Jingjing Gong +1Action Generation Noise-Aware
University of Science and Technology of China · Shanghai Innovation Institute · Fudan University
WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
Jun 3, 2026Ning Yang, Yan Huang, Kaiwen Peng +9Object Goal Navigation Efficient World-Action Model
1Nanjing University · Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences +4
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
May 31, 2026Zemin Yang, Yaoyu He, Yiming Zhong +5Temporally Coherent Imitation Learning Imitation Learning
ShanghaiTech University · Shanghai Jiao Tong University · The Chinese University of Hong Kong +1
Continuous Reasoning for Vision-Language-Action
May 29, 2026Yueh-Hua Wu, Tatsuya Matsushima, Kei OtaAction Generation Reasoning Skills
AIRoA
Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely
May 29, 2026Chalamalasetti Kranti, Sherzod Hakimov, David SchlangenSpatial Reasoning Action Generation
Computational Linguistics, Department of Linguistics University of Potsdam, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany
Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration
May 29, 2026Yusuke Sano, Takeshi ItogaGeneralist Vision--Language--Action Action Generation
Intelligent Systems Laboratory, SECOM Co., Ltd.
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
May 28, 2026Shutong Ding, Zejia Zhong, Zhongyi Wang +4Diffusion-Based Reinforcement Learning Methods Action Generation
1ShanghaiTech University.
GPS-Enhanced Tourist Mobility Modeling with Seasonal Spatial Priors and LLM-Based Activity Chain Generation
May 28, 2026Yifan Liu, Yanling Sang, Xishun Liao +6Mobility Urban Mobility
UCLA Mobility Lab, Department of Civil and Environmental Engineering, University of California, Los Angeles, Los Angeles, USA. · University of Central Florida, Orlando, FL, USA. · Novateur Research Solutions, Ashburn, VA, USA.
ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
May 28, 2026Ye Li, Huanan Liu, Kangye Ji +7Diffusion-Based Vision-Language-Actions Action Generation
Tsinghua University · University of Illinois at Urbana-Champaign
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
May 27, 2026Fangfu Liu, Kai He, Tianchang Shen +7Video World Models World Models
NVIDIA · Tsinghua University · University of Toronto +1
SANTS: A State-Adaptive Scheduler for World Action Models
May 27, 2026Yirui Sun, Guangyu Zhuge, Keliang Liu +4Action Generation World Models
Fudan University · Deep Computing Era Technology Co., Ltd · Harbin Institute of Technology
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
May 27, 2026Junlin WangDiffusion Policies Visuomotor Policy
School of Engineering and Applied Science University of Pennsylvania
Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts
May 21, 2026Zhen Sun, Yongjian Guo, Haoran Sun +6Diffusion-Based Vision-Language-Actions Generalist Vision--Language--Action
Beihang University · JDT AI Infra · Tsinghua University +2
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
May 20, 2026Benedict Quartey, Sebastian Castro, Eric Rosen +3Visuomotor Policy Action Generation
Brown University · Robotics & AI Institute
Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
May 19, 2026Dongjie Yu, Kun Lei, Zhennan Jiang +2Robot Policies Temporally Coherent Imitation Learning
School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR. · Shanghai Qizhi Institute, Shanghai, China. · Shanghai Jiao Tong University, Shanghai, China. +2
SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
May 17, 2026Jingzhi Huang, Junkai Huang, Wenxuan Song +4Vision-Language Navigation Multimodal Large Language Models
Hong Kong Polytechnic University · Institute of Automation, Chinese Academy of Sciences · Hong Kong University of Science and Technology (Guangzhou)
FLASH: Efficient Visuomotor Policy via Sparse Sampling
May 15, 2026Jiaqi Bai, Jindou Jia, Yuxuan Hu +5Visuomotor Policy Action Generation
MARS Lab, Nanyang Technological University, Singapore
Test-time Sparsity for Extreme Fast Action Diffusion
May 13, 2026Kangye Ji, Yuan Meng, Jianbo Zhou +3Diffusion Transformers Diffusion Policies
Tsinghua University · The Chinese University of Hong Kong
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
May 12, 2026Kai Xiong, Hongjie Fang, Lixin Yang +1Robotic Manipulation Action Generation
Shanghai Jiao Tong University
World Action Models: The Next Frontier in Embodied AI
May 12, 2026Siyin Wang, Junhao Shi, Zhaoyang Fu +11Recent World-Action Models World Models
1Fudan University · 2Shanghai Innovation Institute · 3National University of Singapore
HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
May 11, 2026Qiuxuan Feng, Jiale Yu, Jiaming Liu +8Efficient World-Action Model World Models
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · The Chinese University of Hong Kong · Simplexity Robotics
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
May 11, 2026Minqing Huang, Yujiao Xiang, Zihan Liang +7Autonomous Driving Action Generation
Afari Intelligent Drive · University of Electronic Science and Technology of China · Shanghai Jiao Tong University +2
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
May 11, 2026Jianchao Zhao, Huoren Yang, Yusong Hu +6Vision-Language-Action Framework Action Generation
College of Artificial Intelligence, Xi’an Jiaotong University · 2One Robotics · 3Shenzhen University of Advanced Technology
Geometry Guided Self-Consistency for Physical AI
May 9, 2026Yinwei Dai, Zhuofu Chen, Lijie Yang +1Action Generation Diffusion Policies
Princeton University
Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
May 8, 2026Meng Zheng, Samhita Marri, Anwesa Choudhuri +6Action Generation Negative Results
United Imaging Intelligence, Boston, MA, USA · University of Illinois Urbana-Champaign, Urbana, IL, USA
iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
May 5, 2026Jianjie Fang, Yingshan Lei, Qin Wan +8Video World Models World Models
Tsinghua University, China · Northeastern University, China · South China University of Technology, China
Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion
May 2, 2026Jeffrin Sam, Nguyen Khang, Yara Mahmoud +2Action Generation Video Agent
Intelligent Space Robotics Laboratory, Skoltech, Bolshoy Boulevard, 30, Moscow 121205, Russia
Recovering Hidden Reward in Diffusion-Based Policies
May 1, 2026Yanbiao Ji, Qiuchang Li, Yuting Hu +7Diffusion Policies Offline Reinforcement Learning
Shanghai Jiao Tong University · KOKONI 3D
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Apr 27, 2026Fan Du, Feng Yan, Jianxiong Wu +8Action Generation
1Southern University of Science and Technology · 2Xi’an Jiaotong University · 3United Nova Technology +1
CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
Apr 23, 2026Dachong Li, ZhuangZhuang Chen, Jin Zhang +1Action Generation Sparse Spatial Anchors
College of Computer Science and Software Engineering, Shenzhen University · Hong Kong University of Science and Technology · School of Artificial Intelligence, Shenzhen University
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
Apr 23, 2026Xiyin Zeng, Yuyu Sun, Haoyang Li +2Action Prediction Action Generation
1Hong Kong University of Science and Technology (Guangzhou) · 2South China Normal University
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
Apr 22, 2026Xiyang Wu, Zongxia Li, Guangyao Shi +5Agent Skill Retrieval Large Language Model Decisions
University of Maryland · University of Southern California · Good Start Labs +2
InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
Feb 26, 2026Jiahao Liu, Cui Wenbo, Zhongpu Xia +3Real-World Manipulation Tasks Latent Motion
Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Anyverse Dynamics
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
Dec 1, 2025Xavier Thomas, Youngsun Lim, Ananya Srinivasan +2Human Motion Generation Human Motion
Boston University · Belmont High School · Canyon Crest Academy +1
StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
Jul 7, 2025Meng Wei, Chenyang Wan, Xiqian Yu +9Vision-Language Navigation Streaming
1Shanghai AI Lab · 2The University of Hong Kong · 3Zhejiang University +1
3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation
Jan 28, 2025Yueen Ma, Zenglin Xu, Irwin KingDiffusion-Based Vision-Language-Actions Action Generation
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
Date pendingSunghwan Han, Youngtae Han, Youngmin YiFlow-Matching Vision-Language-Action Action Generation
Dept. of Artificial Intelligence, Sogang University, Seoul, 04107, Republic of Korea

Jun 16, 2026, cs.LGJ/K move · Enter open · S save

Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation

Tianyu Wang, Ying Wang, Zhihao Liu, Xi Vincent Wang+1

Department of Production Engineering, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden

Attractors Latent Variable Diffusion Transformers Action Generation

Open paper AskPDF arXiv

Sequential output generation with large-scale Transformer and diffusion decoders pays a memory cost that grows with sequence length, plus iterative per-step computation. Replacing them with small feed-forward decoders restores efficiency but produces unstructured latent representations that limit closed-loop control: phase-conditioned action generation and cross-step latent carry-over both require a latent geometry with stable basins. This article proposes Ghost Attractor Networks, a theoretically derived dynamical decoder whose latent evolves under a learned potential with drift and produces a basin-attractor structure by construction. Three desiderata (multi-modality, decoder-level single-pass switching, and constant memory) motivate the potential-drift form, and mode transitions arise as saddle-node bifurcations with ghost-attractor escape. A hierarchical phase-space decomposition separates first-order basin convergence from second-order proprioceptive refinement. Empirically, a Ghost trained end-to-end with a behavioral-cloning and contrastive objective exhibits the predicted gradient-flow contraction in its potential, with the gradient norm decaying by 67 percent across five integration steps on 1430 held-out samples. Ghost is evaluated as a robotic action decoder. A 2.3-million-parameter Ghost matches the offline accuracy of a 1.07-billion-parameter Diffusion Transformer at 462 times fewer parameters and 32 times lower latency, and beats five alternative 2M-parameter decoders (MLP, Neural ODE, CVAE, Transformer, 1-step Diffusion) on offline mean squared error by 5.9 to 29 percent. On the LIBERO-10 closed-loop benchmark, phase conditioning on Ghost's basin-structured latent yields a 13.5 percentage-point success-rate gain over a feed-forward MLP baseline, and persistent-latent ensembling reaches a 95.7 percent final success rate.

Momentum

Related topics

Latest papers 112