VLMs for Robotics

VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

92 papers in the last four weeks, up 608% on the four weeks before. 0.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 392

All topics

dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
Jun 22, 2026Yuhao Wu, Yitian Liu, Weijie Shen +13Vision-Language-Action Models VLMs for Robotics
ScaleLab at SJTU · 1Shanghai Jiao Tong University · 3Baidu AI Cloud +3
KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies
Jun 22, 2026Yihan Zeng, Minghao Ye, Yiyuan Chen +4Long-Horizon Robotic Manipulation Bimanual Robotic Manipulation
Hong Kong Embodied AI Lab · University of Electronic Science and Technology of China · Shanghai Jiao Tong University +1
Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation
Jun 22, 2026Ali Alabbas, Dipshikha Das, Camillo Murgia +3Zero-Shot Robotic Manipulation Language-Conditioned Robot Manipulation
Department of Electronic, Software and Advanced Manufacturing Engineering, Atlantic Technological University, Galway, Ireland · Atlantic Technological University, Galway, Ireland
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
Jun 22, 2026Lin Sun, Zhiwei Guan, Conglin Wang +7Efficient VLM Inference Efficient VLA Model Inference
JD.com, China · Yiwu Research Institute of Fudan University, China · Tianjin University, China
EgoSteer: An Open-Source Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos
Jun 21, 2026Yifan Zhong, Zhang Chen, Tianrui Guan +15Long-Horizon Robotic Manipulation Robot Skill Learning
Institute for AI, PKU · PKU-PsiBot Joint Lab · UPenn
PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
Jun 21, 2026Xianghui Wang, Feng Chen, Wenbo Zhang +4Efficient VLA Models Vision-Language-Action Models
1Sichuan University · 2Adelaide University · 3Beijing Institute of Technology
Robot Critics that Sweat the Small Stuff
Jun 19, 2026Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan +3Robot Failure Detection VLM Adaptation
Columbia University · Toyota Research Institute
Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation
Jun 18, 2026Zhenghao "Mark'' Peng, Honglin He, Quanyi Li +2Trajectory Generation Robot Navigation
Amazon FAR · UCLA · Independent +1
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
Jun 17, 2026Jisoo Kim, Sangwon Baik, Taeksoo Kim +4Dexterous Manipulation Zero-Shot Robotic Manipulation
Seoul National University · RLWRLD
ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks
Jun 17, 2026Simon Schwaiger, David Seyser, Alessandro Scherl +2Vision-Language Models Vision-Language Grounding
Graz University of Technology, Institute of Software Engineering and Artificial Intelligence · University of Applied Sciences Technikum Wien, Department of Industrial Engineering · 1Graz University of Technology, Institute of Software Engineering and Artificial Intelligence +2
EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation
Jun 17, 2026Zecheng Yin, Benedict Jun MaVLMs for Robotics Object-Goal Navigation
Systems Hub of Intelligence Transportation HKUST(GZ) Guangzhou, Guangdong
Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
Jun 16, 2026Haowen Liu, Xirui Li, Shaoxiong Yao +5Long-Horizon Robotic Manipulation VLM Distillation
University of Maryland College Park · University of Illinois Urbana-Champaign · University of Waterloo +3
PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
Jun 16, 2026Bochen Yang, Lianlei ShanEfficient VLA Models Latent Visual Reasoning
Imperial College London · Tsinghua University
Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
Jun 16, 2026Haoqi Yuan, Zhixuan Liang, Anzhe Chen +20Robot Skill Learning Robot Foundation Models
Qwen Team
GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning
Jun 16, 2026Haoyu Wang, Guoqing Ma, Zeyu Zhang +3LLM Agent Memory Multi-View 3D Reconstruction
School of Computer Science, Peking University · 2CASIA · 3AI2 Robotics
ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning
Jun 15, 2026Wei Xiao, Weiliang Tang, Yuying Ge +4RL for Robotics Robotic Manipulation
1XPENG Robotics · 2Fudan University · 3The Chinese University of Hong Kong +1
CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation
Jun 15, 2026Jan-Niklas Klein, Sona Ghahremani, Christian Medeiros Adriano +1Robot Navigation Semantic Mapping
Hasso Plattner Institute for Digital Engineering, Potsdam, Germany.
Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models
Jun 15, 2026Dongbin Na, Chanwoo Kim, Soonbin Rho +3Robot Navigation Embodied QA
RGA Inc.
Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands
Jun 15, 2026Thanh Nguyen Canh, Thanh-Tuan Tran, Haolan Zhang +3Video Action Recognition Robotic Manipulation
School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan. · University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · Department of Robotics, Hanyang University, Ansan, 15588, Gyeonggi, Korea.
SimWeaver: Zero-Shot RGB Sim-to-Real for Deformable Manipulation
Jun 13, 2026Wenkang Hu, Haoran Wang, Yitong Li +10Zero-Shot Robotic Manipulation Robot Skill Learning
1Shanghai Jiao Tong University · 2Horizon Robotics · 3Style3D Research
Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models
Jun 13, 2026Shenhao Yan, Ge Wang, Qi Liu +7Efficient VLM Inference Efficient VLA Model Inference
Northeastern University · Ising AI · CUHK-Shenzhen
Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
Jun 13, 2026Dianqiao Lei, Lianlei ShanEfficient Inference Efficient VLA Model Inference
1Tsinghua University, Beijing, China.
Guided Diffusion with Distilled Vision-Language Reliability for Aerial Navigation
Jun 11, 2026Ivan Valuev, Iana Zhura, Valerii Serpiva +2Diffusion-Based Planning Robot Navigation
AnyGoal: Vision-Language Guided Multi-Agent Exploration for Training-Free Lifelong Navigation
Jun 11, 2026MoniJesu James, Marcelino Julio Fernando, Miguel Altamirano Cabrera +1Multi-Robot Systems Robot Navigation
See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation
Jun 11, 2026Yoon-Ji Choi, Young-Chae Son, Soo-Chul LimLong-Horizon Robotic Manipulation Bimanual Robotic Manipulation
Dongguk University
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
Jun 11, 2026Dayu Xia, Yue Shi, Yao Mu +7VLM Evaluation Robotic Manipulation
Shanghai AI Laboratory · Zhejiang University · Shanghai Jiao Tong University +2
Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning
Jun 11, 2026Allison Andreyev, Landon Eum, Nestor Tiglao +1Robotic Grasping Zero-Shot Robotic Manipulation
University of Maryland, Cyber-Physical Systems Engineering
AIR-VLA+: Decoupling Movement and Manipulation via Cascaded Dual-Action Decoders with Asymmetric MoE for Aerial Robots
Jun 11, 2026Jianli Sun, Bin Tian, Qiyao Zhang +6VLMs for Robotics Aerial Manipulation
The Institute of Automation, Chinese Academy of Sciences · School of Automation, Beijing Institute of Technology · College of Automotive and Energy Engineering, Tongji University +2
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?
Jun 10, 2026Jadelynn Dao, Milan Ganai, Yasmina Abukhadra +7Test-Time Scaling for VLMs Inference-Time Scaling
Stanford University · University of Waterloo · NVIDIA
Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering
Jun 10, 2026Hyun Joe Jeong, Gokul Swamy, Andrea BajcsyLanguage Model-Based Control Vision-Language-Action Models
Robotics Institute Carnegie Mellon University

Jun 22, 2026, cs.ROJ/K move · Enter open · S save

dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models

Yuhao Wu, Yitian Liu, Weijie Shen, Mishuo Han+12

ScaleLab at SJTU · 1Shanghai Jiao Tong University · 3Baidu AI Cloud+3

Vision-Language-Action Models VLMs for Robotics RL for VLMs

Open paper AskPDF arXiv

Vision-Language-Action (VLA) models have established a powerful paradigm for generalist robotic manipulation by grounding control into the semantic reasoning of VLMs. Prevailing architectures typically model actions continuously via diffusion or flow processes, or discretely through either autoregressive generation or parallel decoding. Recently, Discrete Diffusion VLAs (dVLAs) have emerged as a distinct alternative, unifying vision, language, and action into a single discrete token space via masked generative modeling. While combining iterative refinement with unified representations, its training has thus far been restricted to Supervised Fine-Tuning (SFT), leaving the potential of Reinforcement Learning (RL) for further policy refinement largely unexplored. A fundamental challenge in RL for dVLAs is that the marginal probability of the final action generated by dVLAs remains intractable. To solve this problem, we propose \textbf{dVLA-RL}, shifting the learning objective from the marginal action probability to the joint probability of the sampled generation path. Specifically, by modeling the denoising process as a Markov Decision Process (MDP), we mathematically formulate this path probability as a product of step-wise transitions. This trajectory-level objective provides a unified formulation that natively accommodates variable denoising steps. Leveraging this intrinsic fexibility, we introduce a unified step scheduling approach for complex multi-task learning, tailoring denoising steps to specific task complexities to maximize both success rates and computational effciency. Extensive evaluations demonstrate that our approach achieves a success rate of \textbf{99.7%} on LIBERO. Furthermore, it establishes strong VLA-based results on RoboTwin 2.0 by delivering a \textbf{30.6%} improvement over the SFT baseline, remaining competitive with strong World-Action Model baselines.

Momentum

Related topics

Latest papers 392