{"total":66,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164,"area":null},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2302.08888","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","created":"2023-02-17","cited_by_count":86,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2212.14454","title":"MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid","created":"2022-12-29","cited_by_count":30,"area":null},{"id":"2404.15272","title":"CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2411.18730","title":"Foundation Models in Radiology: What, How, When, Why and Why Not","created":"2024-11-27","cited_by_count":28,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2311.02379","title":"Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models","created":"2023-11-04","cited_by_count":22,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2503.06973","title":"A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis","created":"2025-03-10","cited_by_count":15,"area":null},{"id":"2504.14280","title":"CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey","created":"2025-04-19","cited_by_count":15,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2407.19514","title":"Detached and Interactive Multimodal Learning","created":"2024-07-28","cited_by_count":11,"area":null},{"id":"2409.04758","title":"SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance","created":"2024-09-07","cited_by_count":11,"area":null},{"id":"2303.15256","title":"Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2311.15033","title":"Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones","created":"2023-11-25","cited_by_count":9,"area":null},{"id":"2506.00239","title":"SmellNet: A Large-scale Dataset for Real-world Smell Recognition","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2304.02853","title":"Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-commerce","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2306.09482","title":"Sample-Efficient Learning of Novel Visual Concepts","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2312.07255","title":"GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction","created":"2023-12-12","cited_by_count":8,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2306.07952","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2412.12906","title":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2502.09906","title":"Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2306.09169","title":"Opportunities for Large Language Models and Discourse in Engineering Design","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2409.16145","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2407.15316","title":"AI as a Tool for Fair Journalism: Case Studies from Malta","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2403.06904","title":"Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2504.13218","title":"Harmony: A Unified Framework for Modality Incremental Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2506.20494","title":"Multimodal Representation Learning and Fusion","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2604.10127","title":"VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2310.00783","title":"Propagating Semantic Labels in Video Data","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2406.02780","title":"LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagery","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2403.07888","title":"Cross-modality debiasing: using language to mitigate sub-population shifts in imaging","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2407.07771","title":"Multi-task Prompt Words Learning for Social Media Content Generation","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2507.07135","title":"FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.17598","title":"COLA: Context-aware Language-driven Test-time Adaptation","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2605.24395","title":"AvAtar: Learning to Align via Active Optimal Transport","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2311.03395","title":"Newvision: application for helping blind people using deep learning","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2607.11008","title":"SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.29408","title":"An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.24031","title":"Video-STLayout Pre-training","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}