{"total":340,"rows":[{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"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":"2504.11171","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","created":"2025-04-15","cited_by_count":104,"area":null},{"id":"2306.16623","title":"The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot","created":"2023-06-29","cited_by_count":83,"area":null},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2505.16707","title":"KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models","created":"2025-05-22","cited_by_count":71,"area":null},{"id":"2502.20272","title":"HVI: A New Color Space for Low-light Image Enhancement","created":"2025-02-27","cited_by_count":63,"area":null},{"id":"2410.10329","title":"GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs","created":"2024-10-14","cited_by_count":58,"area":null},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2312.11541","title":"CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare","created":"2023-12-16","cited_by_count":43,"area":null},{"id":"2305.17891","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","created":"2023-05-29","cited_by_count":41,"area":null},{"id":"2503.06073","title":"GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images","created":"2025-03-08","cited_by_count":39,"area":null},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39,"area":null},{"id":"2403.16812","title":"Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making","created":"2024-03-25","cited_by_count":38,"area":null},{"id":"2403.10075","title":"A survey of synthetic data augmentation methods in computer vision","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2404.19094","title":"In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery","created":"2024-04-29","cited_by_count":31,"area":null},{"id":"2411.19378","title":"Libra: Leveraging Temporal Images for Biomedical Radiology Analysis","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2408.00483","title":"A Systematic Review on Long-Tailed Learning","created":"2024-08-01","cited_by_count":28,"area":null},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26,"area":null},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2402.11325","title":"ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models","created":"2024-02-17","cited_by_count":24,"area":null},{"id":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2503.13709","title":"Multi-modal Time Series Analysis: A Tutorial and Survey","created":"2025-03-17","cited_by_count":24,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2410.20346","title":"Historical Test-time Prompt Tuning for Vision Foundation Models","created":"2024-10-27","cited_by_count":22,"area":null},{"id":"2305.19812","title":"A Survey of Label-Efficient Deep Learning for 3D Point Clouds","created":"2023-05-31","cited_by_count":20,"area":null},{"id":"2404.15532","title":"BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis","created":"2024-04-23","cited_by_count":20,"area":null},{"id":"2401.01596","title":"MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries","created":"2024-01-03","cited_by_count":19,"area":null},{"id":"2406.14021","title":"HIGHT: Hierarchical Graph Tokenization for Molecule-Language Alignment","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2510.16990","title":"Graph4MM: Weaving Multimodal Learning with Structural Information","created":"2025-10-19","cited_by_count":17,"area":null},{"id":"2405.03710","title":"Automating the Enterprise with Foundation Models","created":"2024-05-03","cited_by_count":14,"area":null},{"id":"2406.15471","title":"Improving Large Models with Small models: Lower Costs and Better Performance","created":"2024-06-15","cited_by_count":14,"area":null},{"id":"2409.09369","title":"Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology","created":"2024-09-14","cited_by_count":14,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2406.18115","title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12,"area":null},{"id":"2406.05806","title":"Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper","created":"2024-06-09","cited_by_count":12,"area":null},{"id":"2505.18816","title":"Reasoning Segmentation for Images and Videos: A Survey","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2406.14924","title":"DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection","created":"2024-06-21","cited_by_count":11,"area":null},{"id":"2409.09724","title":"MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2410.13384","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2504.12104","title":"Logits DeConfusion with CLIP for Few-Shot Learning","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2505.05517","title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2304.13009","title":"The Potential of Visual ChatGPT For Remote Sensing","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2403.12533","title":"To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions","created":"2024-03-19","cited_by_count":10,"area":null},{"id":"2410.20371","title":"Open-Vocabulary Object Detection via Language Hierarchy","created":"2024-10-27","cited_by_count":10,"area":null},{"id":"2412.14233","title":"Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2505.17330","title":"FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding","created":"2025-05-22","cited_by_count":10,"area":null},{"id":"2305.17185","title":"Task-Driven Lens Design","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2404.12606","title":"ELEV-VISION-SAM: Integrated Vision Language and Foundation Model for Automated Estimation of Building Lowest Floor Elevation","created":"2024-04-19","cited_by_count":9,"area":null},{"id":"2504.10117","title":"AGO: Adaptive Grounding for Open World 3D Occupancy Prediction","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2505.21357","title":"AgriFM: A Multi-source Temporal Remote Sensing Foundation Model for Agriculture Mapping","created":"2025-05-27","cited_by_count":9,"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":"2405.00574","title":"EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2305.17648","title":"Z-GMOT: Zero-shot Generic Multiple Object Tracking","created":"2023-05-28","cited_by_count":7,"area":null},{"id":"2312.16490","title":"Exploring news intent and its application: A theory-driven approach","created":"2023-12-27","cited_by_count":7,"area":null},{"id":"2401.17824","title":"A Survey of Pre-trained Language Models for Processing Scientific Text","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2407.13559","title":"Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2503.05808","title":"DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.17080","title":"Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2507.10095","title":"FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2507.19861","title":"Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos with Practical Quantum Advantage","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2508.04062","title":"PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission Tomography","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2508.17380","title":"Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery","created":"2025-08-24","cited_by_count":7,"area":null},{"id":"2512.04660","title":"I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2602.22056","title":"FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2312.12735","title":"MetaSegNet: Metadata-collaborative Vision-Language Representation Learning for Semantic Segmentation of Remote Sensing Images","created":"2023-12-20","cited_by_count":6,"area":null},{"id":"2406.01843","title":"L-MAGIC: Language Model Assisted Generation of Images with Coherence","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2412.10624","title":"CATALOG: A Camera Trap Language-guided Contrastive Learning Model","created":"2024-12-14","cited_by_count":6,"area":null},{"id":"2412.11917","title":"Does VLM Classification Benefit from LLM Description Semantics?","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2502.14780","title":"ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2503.08420","title":"Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2503.09707","title":"Revisiting semi-supervised learning in the era of foundation models","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2507.11055","title":"Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation","created":"2025-07-15","cited_by_count":6,"area":null},{"id":"2602.00854","title":"Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2606.00095","title":"Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2606.23327","title":"VideoAgent: All-in-One Framework for Video Understanding and Editing","created":"2026-06-22","cited_by_count":6,"area":null},{"id":"2312.00351","title":"Manipulating the Label Space for In-Context Classification","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2405.07163","title":"Realizing Visual Question Answering for Education: GPT-4V as a Multimodal AI","created":"2024-05-12","cited_by_count":5,"area":null},{"id":"2408.04879","title":"On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2410.04546","title":"Learning De-Biased Representations for Remote-Sensing Imagery","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2411.00330","title":"Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification","created":"2024-11-01","cited_by_count":5,"area":null},{"id":"2411.16087","title":"AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2503.07253","title":"AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null}],"next_cursor":"100"}