English
Related papers

Related papers: Fast-dVLA: Accelerating Discrete Diffusion VLA to …

200 papers

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Wenli Xiao , Haotian Lin , Andy Peng , Haoru Xue , Tairan He , Yuqi Xie , Fengyuan Hu , Jimmy Wu , Zhengyi Luo , Linxi "Jim" Fan , Guanya Shi , Yuke Zhu

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling,…

Robotics · Computer Science 2026-04-01 Weiqi Li , Quande Zhang , Ruifeng Zhai , Liang Lin , Guangrun Wang

Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often induce the "seesaw effect": optimizing for one task may…

Computation and Language · Computer Science 2026-01-27 Xiaoyu Liu , Xiaoyu Guan , Di Liang , Xianjie Wu

Large pre-trained models have enabled significant advances in machine learning and served as foundation components. Model fusion methods, such as task arithmetic, have been proven to be powerful and scalable to incorporate fine-tuned…

Machine Learning · Computer Science 2024-03-12 Anke Tang , Li Shen , Yong Luo , Yibing Zhan , Han Hu , Bo Du , Yixin Chen , Dacheng Tao

Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…

Robotics · Computer Science 2026-02-03 Xu Pan , Zhenglin Wan , Xingrui Yu , Xianwei Zheng , Youkai Ke , Ming Sun , Rui Wang , Ziwei Wang , Ivor Tsang

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Robotics · Computer Science 2025-12-17 Zechen Bai , Chen Gao , Mike Zheng Shou

Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalability challenges due…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Xiaohu Jiang , Yixiao Ge , Yuying Ge , Dachuan Shi , Chun Yuan , Ying Shan

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Qiong Wu , Shubin Huang , Yiyi Zhou , Pingyang Dai , Annan Shu , Guannan Jiang , Rongrong Ji

Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving…

Robotics · Computer Science 2026-02-03 Yujie Wei , Jiahan Fan , Jiyu Guo , Ruichen Zhen , Rui Shao , Xiu Su , Zeke Xie , Shuo Yang

With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Runjia Zeng , Cheng Han , Qifan Wang , Chunshu Wu , Tong Geng , Lifu Huang , Ying Nian Wu , Dongfang Liu

The ever-growing volume and decentralized nature of data, coupled with the need to harness it and extract knowledge, have led to the extensive use of distributed deep learning (DDL) techniques for training. These techniques rely on local…

Machine Learning · Computer Science 2024-11-22 Michail Theologitis , Georgios Frangias , Georgios Anestis , Vasilis Samoladas , Antonios Deligiannakis

Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require…

Diffusion models enable high-quality virtual try-on (VTO) with their established image synthesis abilities. Despite the extensive end-to-end training of large pre-trained models involved in current VTO methods, real-world applications often…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Xingzi Xu , Qi Li , Shuwen Qiu , Julien Han , Karim Bouyarmane

In deployment of the VLA models to real-world robotic tasks, execution speed matters. In previous work arXiv:2510.26742 we analyze how to make neural computation of VLAs on GPU fast. However, we leave the question of how to actually deploy…

Robotics · Computer Science 2026-03-30 Chen Yang , Yucheng Hu , Yunchao Ma , Yunhuan Yang , Jing Tan , Haoqiang Fan

Federated learning (FL) has emerged as a key technique for distributed machine learning (ML). Most literature on FL has focused on ML model training for (i) a single task/model, with (ii) a synchronous scheme for updating model parameters,…

Machine Learning · Computer Science 2024-02-19 Zhan-Lun Chang , Seyyedali Hosseinalipour , Mung Chiang , Christopher G. Brinton

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Machine Learning · Computer Science 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs. However, these inputs are often incomplete, resulting in a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Jiahui Zhang , Yurui Chen , Yueming Xu , Ze Huang , Yanpeng Zhou , Yu-Jie Yuan , Xinyue Cai , Guowei Huang , Xingyue Quan , Hang Xu , Li Zhang

Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic control remains challenging. Full fine-tuning (FFT) is prone to overfitting on downstream…

Robotics · Computer Science 2026-05-11 Yuhua Jiang , Junjie Lu , Xinyao Qin , Xiaoyu Chen , Kaixin Wang , Feifei Gao , Li Zhao

The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require additional training stages to become effective…

Machine Learning · Computer Science 2025-10-24 Jacob L. Block , Sundararajan Srinivasan , Liam Collins , Aryan Mokhtari , Sanjay Shakkottai

Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics. We introduce dVLA, a diffusion-based VLA that leverages a multimodal chain-of-thought to unify visual perception, language reasoning, and robotic…

Robotics · Computer Science 2025-10-01 Junjie Wen , Minjie Zhu , Jiaming Liu , Zhiyuan Liu , Yicun Yang , Linfeng Zhang , Shanghang Zhang , Yichen Zhu , Yi Xu