VLA / 视觉-语言-动作模型

GLCM-Based Feature Combination for Extraction Model Optimization in Object Detection Using Machine Learning

Florentina Tatrin Kurniati, Daniel HF Manongga, Eko Sediyono, Sri Yulianto Joko Prasetyo, Roy Rudolf Huizen

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Journal ref JITEKI,December 2023, http://journal.uad.ac.id/index.php/JITEKI/article/view/27842

CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning

Nikunj Gupta, Somjit Nath, Samira Ebrahimi Kahou

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Primitive-based 3D Human-Object Interaction Modelling and Programming

Siqi Liu, Yong-Lu Li, Zhou Fang, Xinpeng Liu, Yang You, Cewu Lu

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Comments AAAI2024

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model

I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan, Nanyun Peng

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Comments Paper accepted by ACL2023 as a main conference paper. The first two authors contribute equally. Code can be publicly accessible at https://github.com/PlusLabNLP/AMPERE

Interaction models for remaining useful life estimation

Dmitry Zhevnenko, Mikhail Kazantsev, Ilya Makarov

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments submitted to Journal of Industrial Information Integration

An agent-based approach to procedural city generation incorporating Land Use and Transport Interaction models

Luiz Fernando Silva Eugênio dos Santos, Claus Aranha, André Ponce de Leon F de Carvalho

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Comments 12 pages, 6 figures, XIX Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2022)

TempAMLSI : Temporal Action Model Learning based on Grammar Induction

Maxence Grand, Damien Pellier, Humbert Fiorino

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Comments Proceedings of the International workshop of Knowledge Engineering for Planning and Scheduling (ICAPS), 2021

Global Interaction Modelling in Vision Transformer via Super Tokens

Ammarah Farooq, Muhammad Awais, Sara Ahmed, Josef Kittler

专题命中 VLA模型 ：action model(title)；分类 cs.CV

FoodChem: A food-chemical relation extraction model

Gjorgjina Cenikj, Barbara Koroušić Seljak, Tome Eftimov

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments 8 pages, 3 figures, 2 tables

Stochastic Local Interaction Model: Geostatistics without Kriging

Dionissios T. Hristopulos, Andreas Pavlides, Vasiliki D. Agou, Panagiota Gkafa

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments 42 pages, 15 figures

Journal ref Mathematical Geosciences, pp.1-43 (2021)

Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling

Tong Chen, Hongzhi Yin, Xiangliang Zhang, Zi Huang, Yang Wang, Meng Wang

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments Manuscript is under review

Asking the Right Questions: Learning Interpretable Action Models Through Query Answering

Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Comments AAAI 2021

Medical Information Retrieval and Interpretation: A Question-Answer based Interaction Model

Nilanjan Sinhababu, Rahul Saxena, Monalisa Sarma, Debasis Samanta

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Comments 39 Pages

Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention

Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu, Antoine Toisoul, Victor Escorcia, Tao Xiang

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Automatic Detection of Satire in Bangla Documents: A CNN Approach Based on Hybrid Feature Extraction Model

Arnab Sen Sharma, Maruf Ahmed Mridul, Md Saiful Islam

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments 5 pages, Conference paper

How Shall I Drive? Interaction Modeling and Motion Planning towards Empathetic and Socially-Graceful Driving

Yi Ren, Steven Elliott, Yiwei Wang, Yezhou Yang, Wenlong Zhang

专题命中 VLA模型 ：action model(title)；分类 cs.RO

Comments accepted to 2019 International Conference on Robotics and Automation

A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling

Martino Mensio, Emanuele Bastianelli, Ilaria Tiddi, Giuseppe Rizzo

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Comments Workshop on Language and Robotics, IROS 2018

WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models

Marine Le Morvan, Jean-Philippe Vert

专题命中 VLA模型 ：action model(title)；分类 cs.LG

Spatio-temporal interaction model for crowd video analysis

Neha Bhargava, Subhasis Chaudhuri

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Comments 13 pages

What Players do with the Ball: A Physically Constrained Interaction Modeling

Andrii Maksai, Xinchao Wang, Pascal Fua

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Cross-view Action Modeling, Learning and Recognition

Jiang wang, Xiaohan Nie, Yin Xia, Ying Wu, Song-Chun Zhu

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Comments CVPR 2014

Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models

Derek Rose, Itamar Arel

专题命中 VLA模型 ：action model(title)；分类 cs.CV

Comments 3 pages, 2 figures, submitted to ICLR2013 workshop

Consistency and Random Constraint Satisfaction Models

J. Culberson, Y. Gao

专题命中 VLA模型 ：action model(title)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 28, pages 517-557, 2007

Science with the Next-Generation VLA and Pulsar Timing Arrays

NANOGrav Collaboration

专题命中 VLA模型 ：VLA(title,comments)

Comments To be published in the ASP Monograph Series, "Science with a Next-Generation VLA", ed. E. J. Murphy (ASP, San Francisco, CA)

Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation

Triplet2Track：一种基于以对象为中心表征的可靠长 horizon 操作分层系统

Jianxiang Liu, Gaojing Zhang, Chuan Wen, Qipeng Liu, Yuxuan Zhao, Ning Guo, Wenzhao Lian

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院） ； School of Engineering and Informatics, University of Sussex（萨塞克斯大学工程与信息学院） 纠错

专题命中 VLA模型 ：VLA(abstract,abstract_cn)；分类 cs.RO、cs.AI

AI总结 针对长 horizon 机器人操作可靠性难题，提出 Triplet-to-Track System（TTS），该闭环模仿学习系统用人类视频减少数据依赖，经实验平均成功率达74.8%，支持对象级与组合泛化。

Comments 8 pages, 6 figures. Accepted for presentation at the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)

Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents

当状态成为攻击面：大语言模型驱动的具身智能体中的状态语义注入

Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu

机构 * Wuhan University（武汉大学） ； University at Buffalo（布法罗大学） 纠错

专题命中 VLA模型 ：vision-language-action(abstract)；action model(abstract)；分类 cs.RO、cs.AI

AI总结 该文聚焦LLM驱动的具身智能体，梳理其技术演进与现有模型，指出其需结合多类信息完成任务落地后执行，为后续状态语义注入攻击研究奠定基础。

Comments submitted to USENIX Security 2027

Q-Learning With World Models

结合世界模型的Q学习

Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh

机构 * Stanford University（斯坦福大学） ； Peking University（北京大学） 纠错

专题命中 VLA模型 ：vision-language-action(abstract)；action model(abstract)；分类 cs.AI、cs.LG

AI总结 本研究提出QWM框架，将世界模型与标准Q学习结合，在真实环境训练中避免复合模型偏差，在Robomimic和LIBERO基准上的样本效率与性能均优于现有SOTA方法。

Prompt-Driven Exploration

提示驱动的探索

Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

机构 * Massachusetts Institute of Technology（麻省理工学院） ； MIT-IBM Computing Research Lab（麻省理工学院-IBM计算研究实验室） ； Improbable AI Lab（英普罗巴布尔人工智能实验室） 纠错

专题命中 VLA模型 ：vision-language-action(abstract)；VLA(abstract)；分类 cs.AI、cs.LG

AI总结 研究针对强化学习中探索难的问题，提出提示驱动的探索策略（PDE），利用视觉-语言模型对轨迹视频推理，从弱策略轨迹中优化提示，实现后验采样，能让强化学习从零奖励起步学习成功策略并提升样本效率。

ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions

ProtoAct：将湿实验室协议转化为具身机器人动作

Zhe Liu, Jiaming Gu, Zhaohui Du, Zhe Wang, Huanbo Jin, Quan Lu, Qi Wang, Ting Xiao, Minting Pan, Dongzhan Zhou

专题命中 VLA模型 ：VLA(abstract,abstract_cn)；分类 cs.RO、cs.AI

AI总结 研究针对湿实验室协议难转化为机器人动作的问题，提出ProtoAct框架，结合ProtoRAG、RefineChecker、ActSchema处理协议，引入BioP2E数据集，经多模型评估与消融实验验证，可实现仿真及真实机器人的协议执行。

Comments 15 pages, 13 figures

NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation

NavVerse：在连续机器人模拟中对室内到室外的具身导航进行基准测试

Junzhe Wu, Yue Hu, Zeyu Han, Po-Hsun Chang, Yinan Dong, Behrad Rabiei, Maani Ghaffari

机构 * University of Michigan（密歇根大学） ； Tsinghua University（清华大学） 纠错

专题命中 VLA模型 ：VLA(abstract,abstract_cn)；分类 cs.RO、cs.CV

AI总结 研究针对机器人在连续场景中从室内到室外的导航问题，引入NavVerse基准，涵盖多种场景和任务。通过可执行接口用多指标评估智能体，零样本实验显示当前智能体在跨上下文导航上差距大，适应是主要瓶颈。