VLA / 视觉-语言-动作模型

LG-NuSegHop: A Local-to-Global Self-Supervised Pipeline For Nuclei Instance Segmentation

Vasileios Magoulianitis, Catherine A. Alexander, Jiaxin Yang, C. -C. Jay Kuo

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Comments 42 pages, 8 figures, 7 tables

Journal ref Asia Pacific Signal and Information Processing Association (APSIPA), 2025 http://www.apsipa.org

A Few-Shot Approach for Relation Extraction Domain Adaptation using Large Language Models

Vanni Zavarella, Juan Carlos Gamero-Salinas, Sergio Consoli

机构 * Department of Mathematics and Computer Science, University of Cagliari, Cagliari, Italy（数学与计算机科学系，卡利亚里大学，卡利亚里，意大利） ； Institute of Data Science and Artificial Intelligence (DATAI), Universidad de Navarra, Pamplona, Spain（数据科学与人工智能研究所（DATAI），纳瓦拉大学，潘普隆，西班牙） ； European Commission, Joint Research Centre (DG JRC), Ispra (VA), Italy（欧洲委员会，联合研究中心（DG JRC），伊斯普拉（瓦拉），意大利） 纠错

专题命中 部署与泛化 ：action model(abstract)；分类 cs.AI

Journal ref CEUR Workshop Proceedings, Vol. 3894 (2024), Workshop at KDD 2024 on Deep Learning and Large Language Models for Knowledge Graphs

ReLI: A Language-Agnostic Approach to Human-Robot Interaction

Linus Nwankwo, Bjoern Ellensohn, Ozan Özdenizci, Elmar Rueckert

机构 * Chair of Cyber-Physical Systems, Technical University of Leoben（技术大学莱博恩首席物理系统 Chair） ； Institute of Machine Learning and Neural Computation, Graz University of Technology（格拉茨技术大学机器学习与神经计算研究所） 纠错

专题命中 部署与泛化 ：action model(abstract)；分类 cs.RO

RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration

Huajie Tan, Xiaoshuai Hao, Cheng Chi, Minglan Lin, Yaoxu Lyu, Mingyu Cao, Dong Liang, Zhuo Chen, Mengsi Lyu, Cheng Peng, Chenrui He, Yulong Ao, Yonghua Lin, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院） 纠错

专题命中 部署与泛化 ：VLA(abstract)；分类 cs.RO

Comments 22 pages, 10 figures

REACT: Runtime-Enabled Active Collision-avoidance Technique for Autonomous Driving

Heye Huang, Hao Cheng, Zhiyuan Zhou, Zijin Wang, Qichao Liu, Xiaopeng Li

专题命中 部署与泛化 ：action model(abstract)；分类 cs.RO

Comments 22 pages, 11 figures

State-Aware IoT Scheduling Using Deep Q-Networks and Edge-Based Coordination

Qingyuan He, Chang Liu, Juecen Zhan, Weiqiang Huang, Ran Hao

专题命中 部署与泛化 ：action model(abstract)；分类 cs.LG

AsyReC: A Multimodal Graph-based Framework for Spatio-Temporal Asymmetric Dyadic Relationship Classification

Wang Tang, Fethiye Irmak Dogan, Linbo Qing, Hatice Gunes

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting

Guoqi Yu, Yaoming Li, Xiaoyu Guo, Dayu Wang, Zirui Liu, Shujun Wang, Tong Yang

专题命中 部署与泛化 ：action model(abstract)；分类 cs.LG

Comments Under Review

PhysMamba: State Space Duality Model for Remote Physiological Measurement

Zhixin Yan, Yan Zhong, Hongbin Xu, Wenjun Zhang, Shangru Yi, Lin Shu, Wenxiong Kang

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark

Liang He, Yougang Chu, Zhen Wu, Jianbing Zhang, Xinyu Dai, Jiajun Chen

专题命中 部署与泛化 ：action model(abstract)；分类 cs.AI

UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures

Mingyuan Zhou, Rakib Hyder, Ziwei Xuan, Guojun Qi

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Comments The project page is at https://mingjoe.github.io/UltrAvatar/

Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers

Moritz Scherer, Luka Macan, Victor Jung, Philip Wiese, Luca Bompani, Alessio Burrello, Francesco Conti, Luca Benini

专题命中 部署与泛化 ：embodied foundation model(abstract)；分类 cs.LG

Comments Accepted for publication at ESWEEK - CASES 2024

Few-Shot Relation Extraction with Hybrid Visual Evidence

Jiaying Gong, Hoda Eldardiry

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Comments 16 pages, 5 figures

Journal ref LREC-COLING 2024

Planning with Dynamically Estimated Action Costs

Eyal Weiss, Gal A. Kaminka

专题命中 部署与泛化 ：action model(abstract)；分类 cs.AI

Comments 3 figures, 2 tables

A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extraction

Muying Luo, Shunping Ji, Shiqing Wei

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Self-supervised Transformer for Deepfake Detection

Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Weiming Zhang, Nenghai Yu

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction

Dongfang Li, Baotian Hu, Qingcai Chen, Tujie Xu, Jingcong Tao, Yunan Zhang

专题命中 部署与泛化 ：action model(abstract)；分类 cs.AI

Comments AAAI 2022

MHFC: Multi-Head Feature Collaboration for Few-Shot Learning

Shuai Shao, Lei Xing, Yan Wang, Rui Xu, Chunyan Zhao, Yan-Jiang Wang, Bao-Di Liu

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Comments Accepted by the 29th ACM International Conference on Multimedia (ACMMM) 2021

Effective Distant Supervision for Temporal Relation Extraction

Xinyu Zhao, Shih-ting Lin, Greg Durrett

专题命中 部署与泛化 ：action model(abstract)；分类 cs.LG

CIM: Class-Irrelevant Mapping for Few-Shot Classification

Shuai Shao, Lei Xing, Yixin Chen, Yan-Jiang Wang, Bao-Di Liu, Yicong Zhou

专题命中 部署与泛化 ：action model(abstract)；分类 cs.CV

Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents

Mohammad Kachuee, Hao Yuan, Young-Bum Kim, Sungjin Lee

专题命中 部署与泛化 ：action model(abstract)；分类 cs.LG

Comments NAACL-HLT 2021

Attention-based model for predicting question relatedness on Stack Overflow

Jiayan Pei, Yimin Wu, Zishan Qin, Yao Cong, Jingtao Guan

专题命中 部署与泛化 ：action model(abstract)；分类 cs.AI

Comments 11 pages, 4 figures, IEEE/ACM MSR 2021

Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression

学习池化：用于灵活多向量压缩的轻量级微调

Stefan Josef

专题命中 部署与泛化 ：action model(abstract)

AI总结 研究后期交互模型部署挑战，提出轻量级微调方法，通过k均值等进行池化感知训练，可跨方法和数据集迁移，多因素训练产生通用模型，最强模型在BEIR SciFact上以83%压缩率且不损精度超越基线。

Comments The 1st Late Interaction Workshop (LIR) @ ECIR 2026

TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation

TF4CTR：通过自适应样本区分的双焦点框架用于CTR预测

Honghao Li, Qiuze Ru, Yiwen Zhang, Yi Zhang, Lei Sang, Yun Yang

专题命中 部署与泛化 ：action model(abstract)

AI总结 本文提出TF4CTR框架，通过自适应样本区分、样本选择嵌入模块和动态融合模块提升CTR预测精度，实验验证其有效性与兼容性。

Comments TCSS accepted

Reviewing the Reviewer: Graph-Enhanced LLMs for E-commerce Appeal Adjudication

审查审查者：图增强的大语言模型用于电商争议裁决

Yuchen Du, Ashley Li, Zixi Huang

机构 * Purdue University（普渡大学） ； Amazon（亚马逊） 纠错

专题命中 部署与泛化 ：action model(abstract)

AI总结 本文提出图增强的大语言模型，通过显式动作建模和冲突建模解决电商争议裁决中的信息不对称问题，提升裁决一致性。

Comments 10 pages, 3 figures, KDD 2026 Applied Data Science Track

Hardware-Accelerated Geometrical Simulation of Biological and Engineered In-Air Ultrasonic Systems

硬件加速的生物与工程空气中超声系统几何模拟

Wouter Jansen, Jan Steckel

专题命中 部署与泛化 ：action model(abstract)

AI总结 SonoTraceUE是一种基于Unreal Engine的高保真声学仿真框架，通过硬件加速的射线追踪和蒙特卡洛衍射模型，实现动态多材料环境中的实时声学传感模拟，用于生物声学研究和机器人闭环系统开发。

MultiCheck: Strengthening Web Trust with Unified Multimodal Fact Verification

MultiCheck: 通过统一多模态事实验证加强网络信任

Aditya Kishore, Gaurav Kumar, Jasabanta Patro

机构 * IISER Bhopal（比哈尔IISER） 纠错

专题命中 部署与泛化 ：action model(abstract)

AI总结 MultiCheck通过统一多模态事实验证框架，提升网络信任，具备高效、透明和抗噪能力。

Joint BS Deployment and Power Optimization for Minimum EMF Exposure with RL in Real-World Based Urban Scenario

联合基站部署与功率优化以最小化电磁场暴露的强化学习在真实世界基于城市场景中

Xueyun Long, Yueheng Li, Mario Pauli, Benjamin Nuss, Thomas Zwick

专题命中 部署与泛化 ：action model(abstract)

AI总结 本文提出了一种基于强化学习的方法，用于在真实世界城市场景中联合优化基站部署与功率配置，以最小化电磁场暴露，同时提高计算效率和准确性。

Modality Alignment with Multi-scale Bilateral Attention for Multimodal Recommendation

Kelin Ren, Chan-Yang Ju, Dong-Ho Lee

专题命中 部署与泛化 ：action model(abstract)

Comments Accepted by CIKM 2025

Geometric deep learning assists protein engineering. Opportunities and Challenges

Julián García-Vinuesa, Jorge Rojas, Nicole Soto-García, Nicolás Martínez, Diego Alvarez-Saravia, Roberto Uribe-Paredes, Mehdi D. Davari, Carlos Conca, Juan A. Asenjo, David Medina-Ortiz

专题命中 部署与泛化 ：action model(abstract)