Vision-Language-Action Models

Also known as VLA

Follow this topic Ask about this topic

Latest papers 1,140

249 papers in the last four weeks, up 144% on the four weeks before. 1.5% of all new papers.

All topics

Grounding Driving VLA via Inverse Kinematics
May 20, 2026Junsung Park, Hyunjung ShimVLMs for Autonomous Driving Vision-Language-Action Models
Korea Advanced Institute of Science and Technology KimJaeChul AI Graduate School 18, Taebong-ro, Seocho-gu, Seoul, South Korea
VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
May 20, 2026Alex S. Huang, Jiahui Zhang, Shiqing Tang +1VLM Evaluation Vision-Language-Action Models
Intelligent Robotics and Vision Lab, University of Texas at Dallas · Allen High School
GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation
May 20, 2026Zijian Zhang, Yuqing Jiang, Qian Cheng +6World Models for Robotics Robotic Manipulation
Tuojing Intelligence · University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences +5
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
May 19, 2026Arash Akbari, Arman Akbari, Masih Eskandar +11Mixed-Precision Quantization VLM Quantization
1Northeastern University · University of Georgia · 3Cisco Systems
Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation
May 19, 2026He-Yang Xu, Pengyuan Zhang, Zongyuan Ge +5VLM Evaluation Robotic Manipulation
Southeast University, China · Monash University, Australia · Xiaomi EV, China +2
RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
May 19, 2026Jingzhou Luo, Yifan Wen, Yongjie Bai +3VLM Robustness Language-Conditioned Robot Manipulation
Sun Yat-sen University, China · Peng Cheng Laboratory · Guangdong Key Laboratory of Big Data Analysis and Processing +1
PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
May 19, 2026Peizheng Guo, Jingyao Wang, Changwen Zheng +1Robot Policy Learning Credit Assignment in RL
Institute of Software Chinese Academy of Sciences · University of Chinese Academy of Sciences
SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
May 19, 2026Kefei Tian, Yuansheng Lian, Kai Yang +2End-to-End Autonomous Driving Risk-Sensitive RL
aCollege of Transportation, Tongji University, Shanghai, 200092, China · bDepartment of Civil Engineering, Tsinghua University, Beijing, 100084, China · cSchool of Vehicle and Mobility, Tsinghua University, Beijing, 100084, China +1
DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs
May 19, 2026Yixiang Zhu, Yonghao Chen, Zijie Yang +2Robotic Control Visuomotor Policy Learning
The Hong Kong University of Science and Technology (Guangzhou) · One Robotics
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
May 19, 2026Chongyu Fan, Gaowen Liu, Mingyi Hong +2Muon Optimizer Vision-Language-Action Models
Michigan State University · Cisco · University of Minnesota +1
Dexora: Open-source VLA for High-DoF Bimanual Dexterity
May 18, 2026Zongzheng Zhang, Jingrui Pang, Zhuo Yang +22Dexterous Manipulation Bimanual Robotic Manipulation
Tsinghua University · Beijing Academy of Artificial Intelligence · The University of Hong Kong +3
Key-Gram: Extensible World Knowledge for Embodied Manipulation
May 18, 2026Jingjing Fan, Siyuan Li, Botao Ren +1Memory-Augmented VLMs Language-Conditioned Robot Manipulation
Department of Computer Science and Technology Tsinghua University · Department of Automation Tsinghua University
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
May 18, 2026Yiyang Fu, Chubin Zhang, Shukai Gong +7Image Corruption Robustness Vision-Language-Action Models
Peking University · Tsinghua University · Astribot +2
From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
May 18, 2026Zhiyuan Feng, Qixiu Li, Huizhi Liang +12Language-Conditioned Robot Manipulation Cross-Embodiment Robot Learning
1Tsinghua University · 5Microsoft Research Asia · 2HKUST +4
AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
May 17, 2026Weijie Kong, Zhian Su, Wei Yu +1Language-Conditioned Robot Manipulation Vision-Language-Action Models
Grasp Lab, School of Mechanical Engineering of Zhejiang University, Hangzhou 310027, China · Torch Kernel Co., Ltd., Hangzhou, 310000, P. R. China
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
May 17, 2026Sixu Lin, Yunpeng Qing, Litao Liu +4Vision-Language-Action Models Multi-Task RL
School of Data Science, The Chinese University of Hong Kong (Shenzhen) · Jiangxing Intelligence Technology Inc. · Zhejiang University +3
CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous Driving
May 17, 2026Ruiyang Zhu, Yuehan He, Boyuan Zheng +4VLMs for Autonomous Driving End-to-End Autonomous Driving
University of Michigan · University of Arizona
Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models
May 17, 2026Nicanor Mayumu, Xiaoheng Deng, Patrick MukalaCoT Faithfulness VLMs for Autonomous Driving
School of Computer Science and Engineering Central South University 932 Lushan Road, Changsha, Hunan P. R. China · School of Computer Science University of Wollongong in Dubai UOWD Building, Dubai Knowledge Park Dubai, United Arab Emirates
Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
May 17, 2026Xinchen Jin, Aditya Chatterjee, Pranav Kumar +1VLM Interpretability Sparse Autoencoders
Department of Computer Science, Purdue University West Lafayette, IN 47907
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
May 16, 2026Miranda Muqing Miao, Subin Kim, Brandon Yang +1VLM Adaptation Vision-Language-Action Models
University of Pennsylvania
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
May 16, 2026Bosung Kim, Ruiyi Wang, David Acuna +5Robot Policy Learning Robot Skill Learning
University of California, San Diego · 2NVIDIA
VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis
May 16, 2026Zeqin Liao, Peifan Ren, Zixu Gao +6VLM Adaptation Synthetic Data Generation for Robotics
School of computing and data science, Nanyang Technological University · School of Software Engineering, Sun Yat-sen University, China and GuangDong Engineering Technology Research Center of Blockchain, China · Northwest A&F University
Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation
May 15, 2026Jin Shi, Brady Zhang, Yishun LuVLM Distillation Efficient VLA Model Inference
Department of Mechanical Engineering University College London London, United Kingdom · Department of Engineering Science University of Oxford Oxford, United Kingdom
Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control
May 15, 2026Hüseyin Arslan, Özgür ErkentRobotic Control Language-Conditioned Robot Manipulation
*Computer Engineering, Hacettepe University, Ankara, Turkey
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
May 15, 2026Jianke Zhang, Yuanfei Luo, Yucheng Hu +6Robotic Manipulation Vision-Language-Action Models
Tsinghua University · ByteDance Seed
PhysBrain 1.0 Technical Report
May 14, 2026Shijie Lian, Bin Yu, Xiaopeng Lin +10VLM Adaptation Vision-Language-Action Models
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
May 14, 2026Zhuohang Li, Liqun Huang, Wei Xu +5Long-Horizon Robotic Manipulation Bimanual Robotic Manipulation
State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University · Shanghai Key Laboratory of Intelligent Robotics, Meta Robotics Institute, Shanghai Jiao Tong University, Shanghai 200240, China · ByteDance Seed +1
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
May 14, 2026Yi Zhang, Yinda Chen, Che Liu +26Action-Conditioned Video Generation Unified Multimodal Models
Beijing Innovation Center of Humanoid Robotics (X-Humanoid) WFM System Group
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
May 14, 2026Tao Lin, Yuxin Du, Jiting Liu +14Language-Conditioned Robot Manipulation Efficient VLA Models
School of AI, Shanghai Jiao Tong University · King Abdullah University of Science and Technology · SJTU-Quic Robot Joint Lab +1
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
May 14, 2026Shijie Lian, Bin Yu, Xiaopeng Lin +8Robot Policy Learning Language-Conditioned Robot Manipulation
1HUST · 2ZGCA · 4HIT +7

May 20, 2026J/K move · Enter open · S save

Grounding Driving VLA via Inverse Kinematics

Junsung Park, Hyunjung Shim

Korea Advanced Institute of Science and Technology KimJaeChul AI Graduate School 18, Taebong-ro, Seocho-gu, Seoul, South Korea

VLMs for Autonomous Driving Vision-Language-Action Models Autonomous Driving Planning

Open paper AskPDF arXiv

Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.