VLA Model Training

VLA: Vision-Language-Action

Follow this topic Ask about this topic

Latest papers

40 papers6 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
Apr 2, 2026Haochen Niu, Kanyu Zhang, Shuyu Yin +3VLA Model Training Vision-Language-Action Models
Shanghai Jiao Tong University, China · Huawei Technologies, China
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
Mar 26, 2026Wenxuan Song, Jiayi Chen, Shuai Chen +8VLA Model Training Vision-Language-Action Models
The Hong Kong University of Science and Technology (Guangzhou) · ShanghaiTech University · Shanghai Institute of Technical Physics, CAS +3
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
Mar 26, 2026Yang Liu, Pengxiang Ding, Tengyue Jiang +10Vision-Language-Action Models VLA Model Training
Westlake University Hangzhou, China · Zhejiang University Hangzhou, China · East China University of Science and Technology Shanghai, China +2
TokenPB: Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
Mar 18, 2026Chen Zhao, Zhuoran Wang, Haoyang Li +6Vision-Language-Action Models VLA Model Training
School of Information, Renmin University of China · Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China · Beijing University of Posts and Telecommunications +1
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
Mar 10, 2026Yutong Hu, Jan-Nico Zaech, Nikolay Nikolov +6Temporal Modeling for VLA Models Vision-Language-Action Models
∗INSAIT, Sofia University “St. Kliment Ohridski” · †KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics · ‡KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images
Adaptive Capacity Allocation for Vision Language Action Fine-tuning
Mar 8, 2026Donghoon Kim, Minji Bae, Unghui Nam +4VLA Model Training Nonlinear LoRA
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
Feb 28, 2026Yuchen Hou, Lin ZhaoVision-Language-Action Models Instruction Generalization in VLA Models
Department of Electrical and Computer Engineering, National University of Singapore, Singapore
Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
Feb 26, 2026Wenxuan Song, Jiayi Chen, Xiaoquan Sun +12Vision-Language-Action Models Efficient VLA Models
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China. · Huazhong University of Science and Technology, Wuhan, China. · Westlake University, Hangzhou, China. +1
VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms
Feb 20, 2026Xiao-Ming Wu, Kang Liao, Yihang Luo +6Robotic Manipulation Vision-Language-Action Models
S-Lab, Nanyang Technological University, Singapore · ACE Robotics · Sun Yat-sen University, China +2
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
Jul 7, 2025Juyi Lin, Amir Taherin, Arash Akbari +11Robotic Control Efficient VLA Model Inference
Northeastern University, Boston, USA · EmbodyX,San Mateo,USA

Apr 2, 2026J/K move · Enter open · S save

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior

Haochen Niu, Kanyu Zhang, Shuyu Yin, Qinghai Guo+2

Shanghai Jiao Tong University, China · Huawei Technologies, China

VLA Model Training Vision-Language-Action Models Data-Efficient Robot Learning Generalization in Robotic Manipulation

Open paper AskPDF arXiv

In real-world robotic manipulation, states typically admit a neighborhood of near-equivalent actions. That is, for each state, there exist a feasible action neighborhood (FAN) rather than a single correct action, within which motions yield indistinguishable progress. However, prevalent VLA training methodologies are directly inherited from linguistic settings and do not exploit the FAN property, thus leading to poor generalization and low sample efficiency. To address this limitation, we introduce a FAN-guided regularizer that shapes the model's output distribution to align with the geometry of FAN. Concretely, we introduce a Gaussian prior that promotes locally smooth and unimodal predictions around the preferred direction and magnitude. In extensive experiments across both reinforced finetuning (RFT) and supervised finetuning (SFT), our method achieves significant improvement in sample efficiency, and success rate in both in-distribution and out-of-distribution (OOD) scenarios. By aligning with the intrinsic action tolerance of physical manipulation, FAN-guided regularization provides a principled and practical method for sample-efficient, and generalizable VLA adaptation.