{"total":141,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332,"area":null},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305,"area":"mllm"},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781,"area":"diffusion"},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520,"area":null},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343,"area":"mllm"},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198,"area":null},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193,"area":"mllm"},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"area":null},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159,"area":"mllm"},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124,"area":null},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115,"area":null},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2405.03162","title":"Advancing Multimodal Medical Capabilities of Gemini","created":"2024-05-06","cited_by_count":90,"area":null},{"id":"2211.06679","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","created":"2022-11-12","cited_by_count":85,"area":null},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2307.15780","title":"LLM-Rec: Personalized Recommendation via Prompting Large Language Models","created":"2023-07-24","cited_by_count":77,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2401.02361","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","created":"2024-01-04","cited_by_count":65,"area":null},{"id":"2401.12425","title":"The Neglected Tails in Vision-Language Models","created":"2024-01-23","cited_by_count":63,"area":"mllm"},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2501.18954","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","created":"2025-01-31","cited_by_count":57,"area":null},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51,"area":"mllm"},{"id":"2305.18980","title":"Multi-modal Queried Object Detection in the Wild","created":"2023-05-30","cited_by_count":47,"area":null},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2307.12813","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","created":"2023-07-24","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39,"area":"mllm"},{"id":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38,"area":"mllm"},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2305.13812","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality","created":"2023-05-23","cited_by_count":32,"area":"mllm"},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32,"area":"rag"},{"id":"2306.01669","title":"Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning","created":"2023-06-02","cited_by_count":30,"area":"mllm"},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"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":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"area":null},{"id":"2306.07890","title":"VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON","created":"2023-06-13","cited_by_count":25,"area":null},{"id":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2504.10685","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results","created":"2025-04-14","cited_by_count":25,"area":null},{"id":"2205.14540","title":"SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners","created":"2022-05-28","cited_by_count":21,"area":null},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20,"area":null},{"id":"2403.06892","title":"Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head","created":"2024-03-11","cited_by_count":20,"area":null},{"id":"2505.20612","title":"Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models","created":"2025-05-27","cited_by_count":20,"area":"mllm"},{"id":"2309.06922","title":"Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning","created":"2023-09-13","cited_by_count":17,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2304.11463","title":"OmniLabel: A Challenging Benchmark for Language-Based Object Detection","created":"2023-04-22","cited_by_count":16,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2304.11619","title":"SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models","created":"2023-04-23","cited_by_count":15,"area":"mllm"},{"id":"2308.13177","title":"How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection","created":"2023-08-25","cited_by_count":15,"area":"mllm"},{"id":"2403.01680","title":"Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"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":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14,"area":"mllm"},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14,"area":null},{"id":"2512.12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval","created":"2025-12-13","cited_by_count":14,"area":null},{"id":"2209.05946","title":"OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network","created":"2022-09-10","cited_by_count":13,"area":null},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","cited_by_count":12,"area":"lr"},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2303.15234","title":"Prompt Tuning based Adapter for Vision-Language Model Adaption","created":"2023-03-24","cited_by_count":10,"area":"mllm"},{"id":"2405.01468","title":"Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models","created":"2024-05-02","cited_by_count":10,"area":"mllm"},{"id":"2503.03987","title":"RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models","created":"2025-03-06","cited_by_count":10,"area":"mllm"},{"id":"2310.15066","title":"Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2501.14369","title":"Low-rank Prompt Interaction for Continual Vision-Language Retrieval","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2310.13683","title":"CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2403.07576","title":"Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2405.19333","title":"Multi-Modal Generative Embedding Model","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2408.11297","title":"Making Large Vision Language Models to be Good Few-shot Learners","created":"2024-08-21","cited_by_count":7,"area":"mllm"},{"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":"2603.18472","title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","created":"2026-03-19","cited_by_count":7,"area":"mllm"},{"id":"2505.21549","title":"Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation","created":"2025-05-25","cited_by_count":6,"area":null},{"id":"2506.23785","title":"Visual Textualization for Image Prompted Object Detection","created":"2025-06-30","cited_by_count":6,"area":"mllm"},{"id":"2509.17191","title":"VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery","created":"2025-09-21","cited_by_count":6,"area":"agents"},{"id":"2307.13697","title":"Benchmarking and Analyzing Generative Data for Visual Recognition","created":"2023-07-25","cited_by_count":5,"area":null},{"id":"2310.01931","title":"MarineDet: Towards Open-Marine Object Detection","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2311.01373","title":"Recognize Any Regions","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2311.08782","title":"Language Semantic Graph Guided Data-Efficient Learning","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2409.19474","title":"FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models","created":"2024-09-28","cited_by_count":4,"area":"mllm"},{"id":"2411.16749","title":"AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks","created":"2024-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2501.05079","title":"Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization","created":"2025-01-09","cited_by_count":4,"area":null}],"next_cursor":"100"}