具身智能 · 全部实体（第 3 / 100 页）

本页收录第 201–300 条，共 9964 条 · 返回 具身智能 首页

• Speaking in Pictures
  Pictures are a fundamental aspect of how we express ourselves, and cave paintings are among our oldest records of intelligence. Yet, despite their importance, why don’t most people feel they can draw, and why are pictures often considered less important than l…
  crossref Neil Cohn 2025-12-16T14:15:32Z 置信度 0.82 cognitive scienceconsciousnessai safetyneuromorphic computinglarge language models
• EVF-SAM: Early Vision-Language Fusion for text-prompted Segment Anything Model
  crossref Yuxuan Zhang, Tianheng Cheng, Lianghui Zhu, Lei Liu 等 2026-06-04T23:45:55Z 置信度 0.66
• 3D-GENERALIST: Vision-Language-Action Models for Crafting 3D Worlds
  Creating 3D graphics content for immersive and interactive worlds remains labor-intensive, limiting our ability to create large-scale synthetic data for training foundation models. Recent methods aim to alleviate this, but they often focus on a single aspect (…
  crossref Fan-Yun Sun, Shengguang Wu, Christian Jacobsen, Thomas Yim 等 2026-05-27T19:40:49Z 置信度 0.82 cs.aics.lgcomputer and information sciencescs.cvcs.cl
• CoachVLM: Vision-Language Model Driven Automatic Sports Technique Assessment and Intelligent Teaching Feedback
  crossref Detai Wang, Shucun Liang, Haiyang Luo 2026-06-16T19:41:22Z 置信度 0.66
• Entity Knowledge Graph Enhanced Vision Language Model for Multi-Organ Diagnosis
  Diagnosing diseases from multiple organs is common in clinical practice but remains challenging. This task demands radiologists' implicit understanding of the structural and functional inter-dependencies within organ systems. Incorporating such anatomical onto…
  crossref Jianxun Yu, Meirui Jiang, Winnie Chiu Wing Chu, Qi Dou 2026-05-20T19:48:46Z 置信度 0.82 computer sciencecs.lgcs.aiartificial intelligencecomputer and information sciences
• Vision language model based panel digit recognition for medical screen data acquisition
  crossref Yizhi Zou, Shuangjie Yuan, Haoyu Liu, Xu Cheng 等 2025-11-13T11:43:01Z 置信度 0.66
• 535 A Scalable Vision-Language Model for Automated Generation of Comprehensive Structured Pathology Reports
  crossref Ke Zheng, Xueyi Zheng, Mu-Yan Cai 2026-03-23T11:39:57Z 置信度 0.66
• Privacy-Preserving Communication-Efficient Federated Transfer Learning with Vision-Language Model for Smart Agricultural Image Classification
  Abstract. Federated learning is attractive for agricultural intelligence because it avoids centralizing farm data, but conventional federated optimization often performs poorly when clients hold non-independent and identically distributed (non-IID) data. This …
  crossref Long Li, Yanbo Huang, Jiajia Li, Dong Chen 等 2026-08-13T15:42:01Z 置信度 0.82 computer and information sciencesmachine learningcs.lgcs.aielectrical engineering, electronic engineering, information engineering
• Proprioception Enhances Vision Language Model in Generating Captions and Subtask Segmentations for Robot Task
  From the perspective of future developments in robotics, it is crucial to verify whether foundation models trained exclusively on offline data, such as images and language, can understand the robot motion. In particular, since Vision Language Models (VLMs) do …
  crossref Kanata Suzuki, Shota Shimizu, Tetsuya Ogata 2026-08-25T19:11:09Z 置信度 0.82 artificial intelligencecomputer sciencecs.cvcomputer and information sciencescs.lg
• Interactive Construction Robots for Timber Truss Assembly via Vision-Language Model and Mark-Based Visual Prompting
  Intelligent construction robots are deemed the future of on-site construction for improved productivity and safety. Despite recent developments in learning-based control methods, effective human–robot interaction remains challenging for construction tasks. To …
  crossref Lei Huang, Qingyu Yan, Zhengbo Zou 2026-01-28T11:03:33Z 置信度 0.82 robotcomputer and information sciencescs.airoboticshuman-computer interaction
• P&ID Information Extraction through a Vision Language Model for Digital Twins
  crossref Rafay Hayat Ali, Chan Young Park, Ashrant Aryal, H. David Jeong 等 2026-01-26T16:17:47Z 置信度 0.66
• Poster: Task-Aware Dynamic Visual Token Pruning for Efficient Vision-Language-Action Inference
  crossref Jianbing Lin, Xiaolei Sun, Weiguang Pang 2026-08-28T19:08:47Z 置信度 0.66
• CurFed-CHARM: Curriculum sequential federated learning with a channel-hierarchical action recognition model for non-IID heterogeneous data in neuromorphic/event cameras
  crossref Muhammad Hamza Zafar, Syed Kumayl Raza Moosavi, Filippo Sanfilippo 2026-02-21T07:19:08Z 置信度 0.66
• What Is Visual Language?
  crossref 2025-12-16T14:15:32Z 置信度 0.63
• HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models
  Vision-Language-Action (VLA) models have recently shown great potential in bridging multimodal perception with robotic control. However, existing methods often rely on direct fine-tuning of pre-trained Vision-Language Models (VLMs), feeding semantic and visual…
  crossref Kun Wang, Xiao Feng, Mingcheng Qu, Tonghua Su 2026-04-21T21:24:02Z 置信度 0.82 computer and information sciencescs.aics.lgcs.cvartificial intelligence
• A Unified Hybrid Encoder–Decoder Model for Vision–Language Image Captioning
  Abstract Image captioning is a combined activity that generates relevant text descriptions of images using natural language processing and computer vision. The outcomes are heavily influenced on the supplied image’s quality and clarity. This research presents …
  crossref Moloy Dhar, Mrinmoy Sen, Bidesh Chakraborty, Suparna Biswas 2026-07-15T18:56:17Z 置信度 0.82 computer scienceartificial intelligencecs.cvcs.cleess.as
• OrbitServe: Joint Energy and Latency Optimization for On-Orbit Vision-Language Model Inference
  crossref Gege Shen, Shuai Yu, Xu Chen, Yaochen Yu 等 2026-07-02T19:42:44Z 置信度 0.66
• Action Research Communities for language teachers
  crossref Angela Gallagher-Brett, Christine Lechner, Tita Mihaiu 2026-06-22T12:08:14Z 置信度 0.66
• VLMoE-Restore: A Vision-Language Model guided Mixture of Experts Framework for Degraded Infrared Image Restoration
  crossref Tao Zhang, Kang Xing 2026-07-27T19:11:32Z 置信度 0.66
• Vision–language foundation model driven agentic AI systems for healthcare
  crossref Lifeng Chen, Xinming Xu, Yiming Qin, Haoxuan Li 等 2026-03-26T09:06:11Z 置信度 0.66
• Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants
  About 283 million people worldwide have visual impairments, motivating research on Visual Language Models (VLMs) for walking assistance. However, existing VLMs for walking assistance often generate redundant and extraneous outputs, hindering users’ situational…
  crossref Chongyang Li, Zhiqiang Yuan, Hanbo Bi, Zexi Jia 等 2026-04-21T21:23:31Z 置信度 0.82 computer and information sciencescs.cvcs.aics.lgcs.cl
• Data Augmentation and Vision-Language Pre-trained Model Transfer for Data-Scarce Disaster Scene Image Classification
  crossref Shanyuan Gu 2026-08-10T19:12:16Z 置信度 0.66
• ReCon: Active Defense against Large Vision-Language Model Jailbreaks via Reverse Safety Concept Injection
  Large Vision-Language Models (LVLMs) confront an escalating threat from sophisticated multimodal jailbreak attacks.However, existing defense strategies suffer from three critical limitations: (1) the neglect of visual threats;(2) a lack of fine-grained specifi…
  crossref Zheng He, Yiwei Wang, Hongxing Wang, Yujun Cai 2026-07-01T12:25:50Z 置信度 0.82 cs.aicomputer and information sciencescs.clartificial intelligencecs.cv
• Real-time safety detection on construction sites using a vision-language and NLP-based model
  crossref S. Sivanraj, D.N.L.S Uduwage, M. Tripathi 2025-09-24T08:50:07Z 置信度 0.66
• CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
  Generalist robots should be able to understand and follow user instructions. Despite providing a powerful architecture for mapping open-vocabulary language instructions to robot actions, current vision-language-action (VLA) models struggle to follow fine-grain…
  crossref Catherine Glossop, William Chen, Arjun Bhorkar, Dhruv Shah 等 2026-08-21T19:11:23Z 置信度 0.82 computer and information sciencescs.aics.cvcomputer sciencecs.lg
• MedProbCLIP: Probabilistic Adaptation of Vision-Language Foundation Model for Reliable Radiograph-Report Retrieval
  crossref Ahmad Elallaf, Yu Zhang, Yuktha Priya Masupalli, Jeong Yang 等 2026-08-04T19:17:28Z 置信度 0.66
• Improved Key Information Extraction Capabilities for Small Vision-Language Model
  crossref Pik Ying Yip, Siu-Kei Au Yeung, Kwok Tai Chui 2026-07-10T00:39:19Z 置信度 0.66
• Read [pdf]> Sustainable Design from Vision to Action by Jeremy Faludi
  crossref Edgardo Barnes 2026-04-28T21:21:25Z 置信度 0.66
• Vision-Language Model-Driven Predictive Platform Employing Swarm Robotics and Post-Quantum Signatures for Autonomous Green Vessel Navigation and Supply Chain Resilience
  This paper proposes an innovative vision-language model (VLM) driven predictive platform that synergistically integrates swarm robotics coordination with post-quantum digital signatures to enable fully autonomous navigation for green vessels eco-friendly ships…
  crossref Selvaprasanth P 2026-01-15T05:50:49Z 置信度 0.82 computer sciencecomputer and information sciencesengineeringbusinesssupply chain
• Integrating Vision and Language: An Improved VAD Model
  Automatic anomaly detection in video surveillance is crucial for public and private safety. However, it is challenging because of unclear abnormal events, limited labeled data, and mismatches between different types of data. Traditional video anomaly detection…
  crossref Manas Ranjan Biswal, Santos Kumar Baliarsingh 2026-03-03T14:20:44Z 置信度 0.82 computer sciencecomputer and information sciencescs.lgcs.cvcs.ai
• CameraTrap-Instruct: A Vision-Language Model for Structured Extraction and Interpreting of Camera Trap Imagery
  Deep learning-based detectors, including YOLO and Faster R-CNN, have recently enabled automated wildlife monitoring from camera trap imagery by identifying species and localizing individuals using bounding boxes. However, these methods primarily emphasize dete…
  crossref Hao Chen, Fang Qiu, Fangchao Dong, Defei Yang 等 2026-03-16T13:20:16Z 置信度 0.82 cs.aiartificial intelligencecomputer and information sciencescs.lgcs.cv
• Vision Spaces (ViSpa) in Language Sciences
  crossref Marco A. Petilli, Fritz Günther 2024-11-11T17:50:32Z 置信度 0.66
• The Language of Action
  crossref David Sebastiani 2025-12-17T07:18:27Z 置信度 0.66
• Mitigating Object and Relationship Hallucination in Large Vision Language Model with Multi-Agent Guidance
  In this paper, we address the hallucination problem in large vision–language models (LVLMs), where fluent descriptions often diverge from the image due to weak visual grounding. To mitigate the problem, we propose Self Evidencing Debate (SED), a training-free …
  crossref Soohyun Kim, Gusang Lee, Kyuhong Shim, Byonghyo Shim 2026-04-21T21:25:57Z 置信度 0.82 computer and information sciencescs.aicomputer sciencecs.lgartificial intelligence
• Identifying Entrance Accessibility in Subsidized Housing Using a Vision Language Model-Assisted Pipeline with a Chain of Refinement
  In subsidized housing with many mobility-restricted residents, securing step-free accessible entrances is crucial, but the lack of data on their availability status at individual dwellings prevents systematic policy support. Currently, collecting such data req…
  crossref Seongju Jang, Gunwoo Yong, Francis Baek, Kimberly Rollings 等 2026-08-27T10:05:16Z 置信度 0.82 computer scienceartificial intelligencecs.lgcs.aicomputer and information sciences
• Efficient Online Peer Adaptation in Multi-Agent Competition and Cooperation via Vision Language Model
  Effectively adapting to unknown peers (partners or opponents) is critical to realistic multi-agent systems. Reinforcement learning methods often struggle in long-horizon tasks with sparse rewards, while recent LLM-driven agents lack a unified framework of coop…
  crossref Yuanfei Wang, Long Ma, Fangwei Zhong, Hao Dong 2026-04-21T21:24:02Z 置信度 0.82 cs.aicomputer and information sciencescs.lgroboticscs.cv
• MultiviewVLM: Unsupervised Multiview Contrastive Language-Image Joint Learning with Pseudo-Labeled Prompts Via Vision-Language Model for 3D/4D Facial Expression Recognition
  crossref Muzammil Behzad 2026-03-19T20:07:53Z 置信度 0.66
• GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model
  Glacial lake monitoring bears great significance in mitigating the anticipated risk of Glacial Lake Outburst Floods. However, existing segmentation methods based on convolutional neural networks (CNNs) and Vision Transformers (ViTs), remain constrained to pixe…
  crossref Lalit Maurya, Saurabh Kaushik, Beth Tellman 2026-08-04T19:18:53Z 置信度 0.82 computer and information sciencescs.aics.cvartificial intelligencecs.lg
• Utilizing Knowledge in Vision-Language Model for Robotic Grasp Force Estimation through Robot-to-Human Image Translation
  In recent years, general-purpose robots have been introduced into domains requiring delicate manipulation, such as materials experimentation. While advances have been made in automating specific processes, generalized robotic pick-and-place operations still po…
  crossref Shohei Hagane, Shigeaki Goto, Yoshihiro Ohama 2026-02-27T20:47:13Z 置信度 0.82 roboticscomputer sciencecomputer and information sciencesartificial intelligencerobot
• RSUniVLM: A unified vision-language model for remote sensing via Granularity-oriented MoE
  crossref Xu Liu, Zhouhui Lian 2026-04-15T07:11:38Z 置信度 0.66
• US-XAI: A Rag-Grounded Vision Language Model for Explainable Urinary Sediment Classification
  Urinary sediment analysis is essential for diagnosing renal and urinary tract disorders, but manual classification of components remains labor-intensive and prone to subjective variability due to visual similarities. Although deep learning (DL) has improved au…
  crossref Ryuichi Ohe, Tasuku Koyama, Hiroki Nishikawa, Ittetsu Taniguchi 等 2026-05-20T19:48:46Z 置信度 0.82 artificial intelligencecs.aicomputer and information sciencescs.lgcs.cv
• Prompt optimization for large language model-driven object detection in complex scenes
  This paper proposes a cue optimization technique for object detection in complex scenarios using a large language model as guidance. By developing a cue optimization algorithm and coupling it closely with the object detection framework, the proposed technique …
  crossref Jinchuan Wei, Ming Ni, Zhixian Tang, Zhiyong Peng 等 2026-04-28T03:13:35Z 置信度 0.78 computer and information sciencescomputer scienceartificial intelligencecs.aicomputer vision and pattern recognition
• Research on Vision-Language Model-Driven Event-Level Hazard Identification Method for UAV Inspection
  crossref Junyang Li, Yiwei Ru, Yongji Liu, Jinfeng Jiang 2026-08-11T19:15:10Z 置信度 0.66
• Action Research Communities for Language Teachers
  How can teachers and teacher educators enact positive change in their working environments?How can they develop professional learning communities? How can they support educational policies on intercultural competence, multilingualism and plurilingualism while …
  crossref 2026-06-22T12:08:14Z 置信度 0.82 psychologymathematics educationgenerative grammarmedical educationknowledge management
• QwenCLIP: Boosting Medical Vision-Language Model Pretraining via LLM Embeddings and Prompt Tuning
  Contrastive Language-Image Pretraining (CLIP) has demonstrated strong generalization for vision-language tasks in computer vision and medical domains, yet its text encoder accepts only up to 77 tokens, which limits its ability to represent long and information…
  crossref Xiaoyang Wei, Camille Kurtz, Florence Cloppet 2026-05-20T19:48:46Z 置信度 0.82 cs.aicomputer scienceartificial intelligencecs.lgcs.cv
• Context-Value-Action Architecture for Value-Driven Large Language Model Agents
  Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current "LLM-as-a-judge" evaluations.By evaluating against empirical g…
  crossref TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang 等 2026-07-01T12:25:50Z 置信度 0.82 cs.aics.lgcomputer and information sciencescs.clcomputer science
• The evolution of end-to-end Vision-Language-Action (VLA) architectures in robotics
  Vision-Language-Action (VLA) models represent a fundamental architectural shift in robotic learning, replacing modular perception-reasoning-control pipelines with unified frameworks that jointly optimize multimodal understanding and motor control. While large …
  crossref Jingjing Pei, Xiaoyin Zheng, Yang Liu, Bike Zhu 等 2026-04-27T11:51:08Z 置信度 0.82 cs.aicomputer and information sciencescomputer scienceartificial intelligencecs.lg
• OOM-Free Alpamayo via CPU-GPU Memory Swapping for Vision-Language-Action Models
  End-to-end Vision-Language-Action (VLA) models for autonomous driving unify perception, reasoning, and control in a single neural network, achieving strong driving performance but requiring 20-60GB of GPU memory-far exceeding the 12-16GB available on commodity…
  crossref Seungwoo Roh, Huiyeong Kim, Jong-Chan Kim 2026-08-28T19:11:15Z 置信度 0.82 computer and information sciencescs.aics.lgelectrical engineering, electronic engineering, information engineeringcs.cl
• Intelligent Food Portioning System Using Vision-Language-Action (VLA) Models for Small-Scale Food Operations
  • Developed intelligent food portioning system for small-scale operations • π0 model achieved 100% success rate with only 30-50 training demonstrations • System adapts across diverse food types: shrimp, grapes, and garlic cloves • Vision-language-action models…
  crossref Ran Yang, Siwei Cai, Lifeng Zhou, Yiming Feng 2026-01-16T16:34:27Z 置信度 0.82 computer sciencecomputer and information sciencesroboticselectrical engineering, electronic engineering, information engineeringcs.ai
• DREAM: Dynamic routing of experts via attention-based mixture for vision-language-action modeling
  crossref Kai Sheng, Liuyi Wang, Zongtao He, Xiao Lin 等 2026-02-25T07:47:45Z 置信度 0.66
• Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models
  Vision-Language-Action (VLA) models pretrained on large-scale multimodal datasets have emerged as powerful foundations for robotic perception and control. However, their massive scale, often billions of parameters, poses significant challenges for real-time de…
  crossref Yifan Ye, Jiaqi Ma, Jun Cen, Zhihe Lu 2026-06-12T19:44:24Z 置信度 0.82 computer and information sciencescs.aics.lgcomputer sciencecs.cv
• Analysis of Vision-Language Models for Underwater Mine Detection and Classification
  crossref Kayeon Kim, Hyunbae Chang, Seokjoon Park, Yoonho Kim 2026-04-14T01:02:20Z 置信度 0.66
• Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
  Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platforms, as well as their associated power budgets, remain poorly understood. This wor…
  crossref Amir Taherin, Juyi Lin, Arash Akbari, Arman Akbari 等 2026-06-18T14:17:19Z 置信度 0.82 computer and information sciencescs.aics.lgcs.cvelectrical engineering, electronic engineering, information engineering
• Sliding-Cache VLA: Training-Free Acceleration of Vision Language Action Models via Foreground-Background Decoupling
  Vision Language Action (VLA) models have demonstrated remarkable potential in robotic applications, yet they encounter substantial latency issues when deployed in real-time scenarios. While current acceleration approaches prove effective, they typically demand…
  crossref Yunqing Jiang, Xiangyuan Chen, Huijia Zhao, Tianlin Liang 等 2026-04-21T21:25:28Z 置信度 0.82 computer and information sciencescs.aics.lgcomputer sciencerobotics
• Action Recognition
  crossref Wei Shen, Chongjie Si, Chen Yang, Yong Yu 2026-01-07T07:32:57Z 置信度 0.63
• DAVLMF-Seg: Vision-language model guided latent frequency-aware diffusion for semi-supervised medical image segmentation
  Medical image segmentation serves as a fundamental step in computer-aided diagnosis and treatment planning. Despite the remarkable progress achieved by fully supervised deep learning models, their performance heavily depends on large-scale, high-quality annota…
  crossref Jiu Jiang, Qi Zhou, Nuo Chen, Haoying He 等 2026-02-10T11:30:22Z 置信度 0.82 computer and information sciencescs.lgcs.cvartificial intelligencecs.ai
• Vision-Controllable Language Model for Image-Guided Story Ending Generation
  Despite the unparalleled capabilities of recently developed large language models (LLMs), controllable natural language generation (NLG) is still a tricky and important problem that aims at satisfying specific constraints in NLG to facilitate practical applica…
  crossref Dizhan Xue, Shengsheng Qian, Changsheng Xu 2026-03-31T19:53:12Z 置信度 0.82 cs.aicomputer sciencecs.lgcs.clartificial intelligence
• Zero-shot performance of a general-purpose vision-language model for pediatric appendicitis diagnosis
  Background General-purpose vision-language models can analyze medical images without task-specific training, but their value for pediatric abdominal ultrasound is unknown. Objective To investigate the zero-shot performance of a general-purpose vision-language …
  crossref Ceren Altintas Mese, Ismail Mese, Tugba Akinci D’Antonoli 2026-06-08T08:21:09Z 置信度 0.82 medicineartificial intelligencecs.aimedical physicscs.cv
• How Good is my Histopathology Vision-Language Foundation Model? A Holistic Benchmark
  crossref Roba Al Majzoub, Hashmat Malik, Muzammal Naseer, Muhammad Zaigham Zaheer 等 2026-01-26T16:36:54Z 置信度 0.66
• SUSTAIN-VLM: Coordinated Data and Compute for Low-Carbon Vision Language Model Fine-Tuning
  Training and fine-tuning vision–language models (VLMs) consume substantial energy, while grid carbon intensity varies by time and region. We present SUSTAIN-VLM, a carbon-elastic framework that co-adapts (i) data selection via a carbon-elastic curriculum (CEC)…
  crossref Hassan Khan, Sunbal Iftikhar, Steven Davy, John G. Breslin 2026-04-21T21:23:31Z 置信度 0.82 greenhouse gascarbon fiberscs.aicomputer vision and pattern recognitioncarbon capture and storage
• VLM-MPC: Model predictive controller augmented vision language model for autonomous driving
  crossref Keke Long, Haotian Shi, Jiaxi Liu, Chaowei Xiao 等 2025-12-05T17:31:44Z 置信度 0.66
• Foundation of vision-language models
  crossref Yingchao Zhang, Cheng Liu 2026-05-01T08:51:15Z 置信度 0.66
• Voice-Controlled Robotic Arm System for Tabletop Manipulation via Large Language Model and 3D Vision
  crossref Supakorn Thavornvong, Anapat Kitsommart, Mahannop Thabua, Chutiya Thanaluck 等 2026-07-30T19:07:59Z 置信度 0.66
• A Hybrid CNN–Vision Language Model Framework for Visual Fire Detection and Context-Aware Decision Support in Oil and Gas Facilities
  Abstract In Nigeria's oil and gas industry, fire and explosion incidents have claimed more than 3,400 lives over the last 15 years, which are fueled by old infrastructure, chronic pipeline vandalism and lack of intelligent real time monitoring. Traditional sen…
  crossref E. C. Ashinze, E. P. Okoneyo 2026-08-10T00:12:06Z 置信度 0.82 artificial intelligencecomputer sciencecomputer and information sciencescs.aics.cv
• ConVLM: Context-guided vision-language model for fine-grained histopathology image classification
  • ConVLM addresses the limitation of coarse alignment in existing VLMs by introducing context-guided token learning and enhancement, enabling fine-level image-text interaction that captures subtle morphological details in histology images. • The model selectiv…
  crossref Anabia Sohail, Iyyakutti Iyappan Ganapathi, Basit Alawode, Sajid Javed 等 2025-09-18T07:01:09Z 置信度 0.82 cs.lgcs.aicomputer and information sciencesartificial intelligencecs.cv
• Mixture of coarse and fine-grained prompt tuning for vision-language model
  crossref Yansheng Gao, Zixi Zhu, Shengsheng Wang 2025-07-02T11:52:24Z 置信度 0.66
• Stable Evidence, Unstable Decisions: An Empirical Analysis of Model Decision Stability in Vision–Language Models
  VLMs provide visual information alongside their predictions, but it remains unclear whether consistency in such information implies consistent decisions.We study this question in a controlled medical-imaging setting using brain MRI with pathologyconfirmed labe…
  crossref Ali Khoramfar, Mohammad Javad Dousti, Alireza Mohamadian, Heshaam Faili 2026-07-01T12:25:50Z 置信度 0.82 cs.aimedicineai governancepsychologysocial and behavioral sciences
• WSTC: Task-adaptive medical vision–language model with semantic tokens and dynamic alignment
  crossref Xiaolan Gao, Jiaorao Wang, Dan Yang 2026-02-13T08:08:07Z 置信度 0.66
• Cluster-aware prompt ensemble learning for few-shot vision-language model adaptation
  • Introduces CAPEL: ensembles multiple prompts in logit space for VLM adaptation. • Preserves multimodal class structure and supports fully batched inference. • Uses cluster-preserving entropy to stabilize diverse prompt subclassifiers. • Learns prompt-level a…
  crossref Zhi Chen, Xin Yu, Xiaohui Tao, Yan Li 等 2025-10-19T14:32:41Z 置信度 0.82 cs.aicomputer and information sciencesartificial intelligencecs.cvcs.lg
• Design and Implementation of a Multimodal Vision-Language Model for Remote Sensing Applications
  crossref Lingjun Kong, Fangxiu Liu, Yudong Zhang, Dedong Wu 2026-08-07T19:17:38Z 置信度 0.66
• The Evaluation Bottleneck of Vision-Language-Action Models: A Evaluation-Centric Survey
  Vision-Language-Action (VLA) models are advancing faster than the field can evaluate them reliably. Researchers use different metrics and lab-specific protocols, making it hard to tell whether reported gains reflect genuine progress or favorable evaluation cho…
  crossref Zirui Song, Huaxing Liu, Xiang Wang, Shuai Li 等 2026-06-08T02:07:00Z 置信度 0.82 artificial intelligencecomputer and information sciencescs.lgcs.aicomputer science
• STAR Block: Adaptive spatio-temporal recalibration for action quality assessment
  crossref Junhao Sun, Lanfei Zhao 2026-01-12T16:27:05Z 置信度 0.63
• The Model for Rhetorical Action
  The Encyclopedia of Arabic Rhetoric's \"Model for Rhetorical Action\" distinguishes between four analytically distinct, sequential levels of every rhetorical action.
  crossref Mandar Marathe 2026-08-08T11:39:56Z 置信度 0.76 intensive care medicineai governancemedical educationcs.crblockchain
• Retraction notice to “Handcrafted localized phase features for human action recognition” [Image and Vision Computing 123 (2022) 104465]
  crossref Seyed Mostafa Hejazi, Charith Abhayaratne 2026-03-22T04:06:33Z 置信度 0.66
• <p>Reproducibility And Accuracy of Large Language Model Vision Apis for Carbohydrate Estimation from Food Photographs: A Four-Model Batch Comparison with Implications for Automated Insulin Dosing </p>
  Aims/hypothesis: <br>  We aimed to characterize the within-image reproducibility of carbohydrate estimates from four large language model (LLM) vision APIs and to quantify the clinical risk for insulin dosing, stratifying accuracy by reference v…
  crossref Tim Street 2026-04-26T05:53:06Z 置信度 0.82 artificial intelligencecs.aimedicinecomputer sciencebrain-computer interface
• Attention Heatmap Drift in a Contrastively Pretrained Vision–Language Model: A Controlled Matched-Learning-Rate Comparison of Full Fine-Tuning and Low-Rank Adaptation
  Downstream adaptation of a contrastively pretrained vision--language model can improve in-domain accuracy while degrading performance on unseen transfer tasks. This study examines how full fine-tuning and low-rank adaptation alter attention heatmaps under a co…
  crossref Ruize Xia 2026-04-07T00:32:22Z 置信度 0.82 cs.aiartificial intelligencecomputer sciencecomputer and information sciencescs.lg
• Transformer-Enhanced YOLO11 and Vision–Language Model for Intelligent Classroom Behavior Monitoring
  Monitoring student behavior is central to understanding classroom engagement and supporting adaptive educational management. Traditional observation methods are labor-intensive and subjective, limiting their scalability and accuracy. With advances in artificia…
  crossref Shihong Zhu, Qingyun Fang, Rongyue Zheng, David Z. Zhu 2026-07-31T18:07:33Z 置信度 0.82 computer sciencecs.aicomputer and information scienceselectrical engineering, electronic engineering, information engineeringcs.lg
• Robustness of Large Vision Language Model Features Under Wireless Channel Degradation for Medical Visual Question Answering
  Deploying medical visual question answering (VQA) systems over wireless networks introduces a fundamental challenge: channel-induced image degradation may corrupt the visual representations extracted by large vision-language models (VLMs), leading to unreliabl…
  crossref Merve Güllü, Necaattin Barışçı 2026-06-30T02:11:57Z 置信度 0.82 computer and information sciencescs.aiartificial intelligencecs.cvcs.lg
• SIRModel: Learning Spatial Intermediate Representation to Parameter-Efficiently Fine-Tune a Vision Language Model for Manipulation
  Long-horizon robotic manipulation requires a policy to bridge task-level semantic reasoning with metric three-dimensional interaction geometry. Existing vision–language–action policies usually acquire geometry implicitly from visual tokens or introduce determi…
  crossref Li Lin, Minghao Shi, Tenglong Wang 2026-08-31T04:24:03Z 置信度 0.82 computer and information sciencescs.airoboticsartificial intelligencecs.lg
• PerVL-Bench: Benchmarking Multimodal Personalization for Large Vision–Language Models
  In recent years, personalization, which utilizes user-specific data to generate tailored responses, has been increasingly adopted in user-centric domains. However, while Large Language Models (LLMs) are actively researched, the exploration of the personalizati…
  crossref Minsung Kim 2026-05-05T19:59:32Z 置信度 0.82 computer sciencecs.aics.clcs.lgcomputer and information sciences
• Establishing an action research community to develop language teaching
  crossref Sona Hakobyan, Luiza Marabyan 2026-06-22T12:08:14Z 置信度 0.66
• Sustainable teacher development through conducting action research
  crossref Kenan Dikilitaş 2026-06-22T12:08:14Z 置信度 0.63
• AFRNet: Adaptive feature recalibration network for efficient multimodal action recognition
  crossref Shaocan Liu, Xiaopeng Fan, Debin Zhao 2026-08-25T06:57:02Z 置信度 0.63
• ConvoCrop Vision Language Model for Rice Disease Detection
  The rapid spread of rice diseases for instance, brown spot, bacterial blight, and blast are a threat to food security in major rice-producing regions. However, timely and accurate diagnosis remains a bottleneck for smallholder researchers and farmers. To addre…
  crossref Qurat Ul Ain Fatima, Saad Hassan Butt, Muhammad Asfand e Yar, Anwar Iqbal 等 2026-06-11T19:58:28Z 置信度 0.82 cs.aics.cvcs.cltaxonomynatural language processing
• VLM-APMatch: A Vision-Language Model Framework for Cross-Document Matching and Reconciliation in Accounts Payable
  crossref Mikael Kevin, Dodi Sudiana 2026-08-12T19:19:29Z 置信度 0.66
• Enhancing usability in face privacy protection via vision-language guided diffusion model
  crossref Zhifeng Xu, Peiyao Yuan, Yiru Zhao, Lei Zhao 2025-09-30T02:55:31Z 置信度 0.66
• SGAC: A Scene Graph-Guided Vision-Language Understanding Framework for Action Reasoning
  Despite their central role in multimodal semantic understanding, current vision–language models exhibit persistent limitations in capturing dynamic interactions and reasoning about action intentions in images, which constrains comprehensive understanding of ev…
  crossref Jiaming Wang, Ziyin Gu, Qingmeng Zhu, Zhipeng Yu 等 2026-04-21T21:25:57Z 置信度 0.82 cs.aicomputer vision and pattern recognitioncs.lgcs.cvcs.cl
• Radiologist‑vision‑language model collaboration for breast cancer diagnosis in mammography
  crossref Zhengbo Zhou, Dooman Arefan, Jules Sumkin, Shandong Wu 2026-04-02T21:07:00Z 置信度 0.66
• Dialectmind@DravidianLang Tech 2026: Zero-Shot Dialectal Tamil Automatic Speech Recognition Using a Large Pretrained Conformer Model
  The low-resource dialectal Automatic Speech Recognition (ASR) in languages like Tamil is a critical issue because of phonological differences, lack of labeled data and because of the differences in the acoustic of speech patterns among regions.This paper will …
  crossref Gayathri.k, Bharathi B 2026-07-01T12:25:50Z 置信度 0.78 cs.sdeess.ascs.clcs.lgcs.ai
• Vision Language Model-Driven Multimodal Occlusion Analysis (VLM-MOA) Method for Construction Progress Monitoring
  Accurate and timely construction progress updates are vital for effective project management. Drone-based data collection offers a cost-effective, efficient method for generating point cloud scans to visualize and track progress. However, limitations in drone …
  crossref W. Ya, L. Peihang, W. Mudan, M. Agata 等 2026-01-28T11:05:37Z 置信度 0.82 computer scienceartificial intelligencecomputer and information sciencescs.aics.lg
• Multi‐Grained Vision–Language Alignment for Domain Generalised Person Re‐Identification
  ABSTRACT Domain generalised person re‐identification (DG Re‐ID) is a challenging task, where models are trained on source domains but tested on unseen target domains. Although previous pure vision‐based models have achieved significant progress, the performanc…
  crossref Jiachen Li, Xiaojin Gong, Dongping Zhang 2026-03-08T14:56:18Z 置信度 0.82 computer scienceartificial intelligencecs.cvcomputer and information sciencescs.ai
• SAViL-Det: Semantic-Aware Vision-Language Model for Multi-script Text Detection
  crossref Mohammed-En-Nadhir Zighem, Abdenour Hadid 2026-01-02T00:11:12Z 置信度 0.66
• TriFusion-RL: Integrating task verifiers, self-feedback, and perceptual tools for vision-language models
  crossref Xiaowei Wang 2026-04-16T15:45:29Z 置信度 0.66
• Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
  Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained knowledge. However, exi…
  crossref Xiwen Chen, Wenhui Zhu, Peijie Qiu, Hao Wang 等 2026-05-05T19:59:32Z 置信度 0.82 computer and information sciencescs.cvcs.lgcs.aielectrical engineering, electronic engineering, information engineering
• MO-VLA: Preference Adaptation for Vision-Language-Action Models via Multi-Objective Reinforcement Learning
  Vision-Language-Action (VLA) models trained with large-scale behavior cloning (BC) have achieved substantial progress in producing diverse and complex robotic behaviors, and have been widely deployed on robot manipulation, human-robot cooperation, and autonomo…
  crossref Yan Yang, Yuquan Wu, Mingxuan Jing 2026-06-08T21:31:15Z 置信度 0.82 computer sciencecomputer and information sciencescs.lgcs.aiartificial intelligence
• Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance
  crossref Xunchu Zhou, Xiaohong Liu, Yunlong Dong, Tengchuan Kou 等 2026-03-06T09:40:30Z 置信度 0.66
• PI-VLA: Adaptive Symmetry-Aware Decision-Making for Long-Horizon Vision–Language–Action Manipulation
  Vision–language–action (VLA) models often suffer from limited robustness in long-horizon manipulation tasks—where robots must execute extended sequences of actions over multiple time steps to achieve complex goals—due to their inability to explicitly exploit s…
  crossref Yina Jian, Di Tian, Xuan-Jing Chen, Zhen-Yuan Wei 等 2026-02-24T13:53:20Z 置信度 0.82 computer and information sciencescs.aiartificial intelligenceroboticscomputer science
• Testing Vision-Language Models with Human Visual Search Principles
  Can behavioural tests from cognitive science really tell us whether vision-capable AI systems “see” the world in human-like ways—or only appear to?
  crossref Jonathan Edward Prunty 2026-03-24T02:00:14Z 置信度 0.74
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
  Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera perspectives, the model…
  crossref Tianyi Zhang, Haonan Duan, Haoran Hao, Yu Qiao 等 2026-03-18T01:03:07Z 置信度 0.82 computer and information sciencesartificial intelligenceroboticscs.aicomputer science
• Notes
  crossref 2025-12-16T14:15:32Z 置信度 0.59