TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control
Institute for Infocomm Research (I$^2$R), A*STAR, Singapore(信息通信研究所(I²R),A*STAR,新加坡);Tsinghua University, Beijing, China(清华大学,北京,中国);Nanyang Technological University, Singapore(南洋理工大学,新加坡)
Yuteng Sun, Haoran Wang, Ruofei Bai, Zhengguo Li, Jun Li, Meng Yee Michael Chuah, Wei Yun Yau
Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency because they adopt a low-frequency batch-and-execute paradigm. This frequency mismatch creates an execution blind spot, causing failures in dynamic environments where targets move during the open-loop execution window. We propose TIDAL (Temporally Interleaved Diffusion and Action Loop), a hierarchical framework that decouples semantic reasoning from high-frequency actuation. TIDAL operates as a backbone-agnostic scheduler for diffusion-based VLAs, using a dual-frequency architecture to redistribute the computational budget. Specifically, a low-frequency macro-intent loop caches semantic embeddings, while a high-frequency micro-control loop interleaves single-step flow integration with execution, conditioning on the latest state fused with motion cues. To handle the resulting latency shift, we introduce a temporally misaligned training strategy where the policy learns stalenessaware compensation, conditioning on stale semantic intent alongside real-time proprioception. TIDAL is architectural, making it orthogonal to system-level optimizations. Experiments show an average 2.5x performance gain over open-loop baselines in dynamic interception tasks. Despite a slight decrease in static success rates, our approach yields a 4x increase in feedback frequency and extends the effective horizon of semantic embeddings beyond the native action chunk size. Under nonpaused physics and on a real robot, TIDAL remains robust to unmodeled dynamics, while standard open-loop baselines fail due to latency-induced error accumulation.
Non-Markovian Long-Horizon Robot Manipulation via Keyframe Chaining
Tongji University(同济大学);University of Technology Sydney(技术悉尼大学);University of Electronic Science and Technology of China(电子科学与技术大学);Advanced Institute of Big Data(大数据先进研究院)
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics(库勒恩大学,机械工程系,机器人、自动化与机电一体化研究单位);KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images(库勒恩大学,电气工程系,语音和图像处理研究单位)
SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);Nanyang Technological University(南洋理工大学);Zhejiang University(浙江大学)
Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院);University of Science and Technology of China(中国科学技术大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));BAAI(北京人工智能研究院)
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
School of Computer Science and Engineering, Sun Yat-sen University, China(中山大学计算机科学与工程学院);AMap, Alibaba Group(阿里巴巴集团高德地图);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China(教育部机器智能与先进计算重点实验室)
Chain of World: World Model Thinking in Latent Motion
Harbin Institute of Technology(哈尔滨工业大学);Li Auto;Beijing Academy of Artificial Intelligence (BAAI)(北京人工智能研究院);University of New South Wales(新南威尔士大学);Chongqing Research Institute of HIT(哈尔滨工业大学重庆研究院);Peking University(北京大学)
Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control
Electrical and Computer Engineering Department, University of New Mexico, Albuquerque, United States, 87106(电气与计算机工程系,新墨西哥大学,阿尔伯克基,美国,87106);Dynamic Robot Systems Group, Oxford Robotics Institute, University of Oxford, United Kingdom, OX26NN(动态机器人系统组,牛津机器人研究所,牛津大学,英国,OX26NN);Mechanical and Aerospace Engineering Department, The George Washington University, DC, United States, 22202(机械与航空航天工程系,乔治华盛顿大学,华盛顿特区,美国,22202);Department of Computer Science, University of Alabama at Birmingham, Alabama, United States, 35294(计算机科学系,阿拉巴马大学伯明翰分校,阿拉巴马,美国,35294);The School of Computation, Information and Technology, Technical University of Munich, Germany, 85748(计算、信息与技术学院,慕尼黑技术大学,德国,85748);Department of Mechanical Engineering, Politecnico di Milano, Milan, Italy, 20156(机械工程系,米兰理工学院,米兰,意大利,20156)
Graph-Fused Vision-Language-Action for Policy Reasoning in Multi-Arm Robotic Manipulation
Machine Learning and I-health International Cooperation Base of Zhejiang Province, Artificial Intelligence Institute, Hangzhou Dianzi University, Zhejiang(浙江省机器学习与健康国际合作基地、人工智能学院、杭州电子大学);Electrical and Computer Engineering Department, The University of New Mexico(新墨西哥大学电气与计算机工程系);School of Computation, Information and Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院)
Research Institute of Tsinghua University in Shenzhen(清华大学深圳研究院);Everwise-Tech Co., Ltd.(恒智慧科技有限公司);Tongji University(同济大学);Fudan University(复旦大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Department of Automation, BNRist, Tsinghua University(自动化系、BNRist、清华大学);Dexmal;MEGVII Technology(MEGVII技术);Tianjin University(天津大学);Harbin Institute of Technology(哈尔滨工业大学);StepFun