{"total":217,"rows":[{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005,"area":"mllm"},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205,"area":"mllm"},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90,"area":"lr"},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2407.08303","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","created":"2024-07-11","cited_by_count":73,"area":"mllm"},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70,"area":"mllm"},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2312.01701","title":"Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites","created":"2023-12-04","cited_by_count":61,"area":"mllm"},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2312.00825","title":"SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples","created":"2023-11-30","cited_by_count":53,"area":"mllm"},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"area":"mllm"},{"id":"2408.15881","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","created":"2024-08-28","cited_by_count":45,"area":"mllm"},{"id":"2409.01156","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","created":"2024-09-02","cited_by_count":40,"area":"inference"},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38,"area":"mllm"},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38,"area":"lr"},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36,"area":null},{"id":"2410.02746","title":"Contrastive Localized Language-Image Pre-Training","created":"2024-10-03","cited_by_count":33,"area":"mllm"},{"id":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32,"area":null},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29,"area":"mllm"},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2410.05249","title":"LoTLIP: Improving Language-Image Pre-training for Long Text Understanding","created":"2024-10-07","cited_by_count":27,"area":null},{"id":"2311.03964","title":"Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining","created":"2023-11-07","cited_by_count":25,"area":"lr"},{"id":"2406.11451","title":"CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation","created":"2024-06-17","cited_by_count":25,"area":"lr"},{"id":"2410.01768","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","created":"2024-10-02","cited_by_count":25,"area":null},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2306.11593","title":"Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2403.16831","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","cited_by_count":17,"area":"mllm"},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2411.14452","title":"Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2506.19848","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2406.05271","title":"USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2410.02740","title":"Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models","created":"2024-10-03","cited_by_count":14,"area":null},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2412.00440","title":"Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training","created":"2024-11-30","cited_by_count":13,"area":"mllm"},{"id":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2604.12012","title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","created":"2026-04-13","cited_by_count":13,"area":"mllm"},{"id":"2402.06015","title":"Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing","created":"2024-02-08","cited_by_count":12,"area":"mllm"},{"id":"2409.19425","title":"Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment","created":"2024-09-28","cited_by_count":12,"area":"mllm"},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2505.09372","title":"MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment","created":"2025-05-14","cited_by_count":12,"area":"mllm"},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":11,"area":null},{"id":"2411.04997","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation","created":"2024-11-07","cited_by_count":11,"area":null},{"id":"2507.22431","title":"HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models","created":"2025-07-30","cited_by_count":11,"area":"mllm"},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2408.12023","title":"Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2503.05186","title":"Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions","created":"2025-03-07","cited_by_count":10,"area":"mllm"},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2410.10308","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","created":"2024-10-14","cited_by_count":9,"area":"mllm"},{"id":"2411.07461","title":"BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions","created":"2024-11-12","cited_by_count":9,"area":"mllm"},{"id":"2504.16801","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","created":"2025-04-23","cited_by_count":9,"area":"distill"},{"id":"2603.09160","title":"RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning","created":"2026-03-10","cited_by_count":9,"area":"mllm"},{"id":"2307.11315","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","created":"2023-07-21","cited_by_count":8,"area":"mllm"},{"id":"2508.18067","title":"Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2606.09393","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","created":"2026-06-08","cited_by_count":8,"area":"mllm"},{"id":"2310.01330","title":"Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association","created":"2023-10-02","cited_by_count":7,"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":"2403.08059","title":"FluoroSAM: A Language-promptable Foundation Model for Flexible X-ray Image Segmentation","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2405.10286","title":"FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models","created":"2024-05-16","cited_by_count":7,"area":"mllm"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2408.01460","title":"LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models","created":"2024-07-27","cited_by_count":7,"area":null},{"id":"2408.14744","title":"RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models","created":"2024-08-27","cited_by_count":7,"area":"mllm"},{"id":"2410.06777","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","created":"2024-10-09","cited_by_count":7,"area":"mllm"},{"id":"2410.23370","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","created":"2024-10-30","cited_by_count":7,"area":"mllm"},{"id":"2411.12044","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","created":"2024-11-18","cited_by_count":7,"area":"mllm"},{"id":"2502.09598","title":"GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image Analysis","created":"2025-02-13","cited_by_count":7,"area":"mllm"},{"id":"2502.12513","title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","created":"2025-02-18","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":"2508.11317","title":"Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2509.01644","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2511.17209","title":"Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers","created":"2025-11-21","cited_by_count":7,"area":null},{"id":"2402.15120","title":"Fine-tuning CLIP Text Encoders with Two-step Paraphrasing","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2409.09721","title":"Finetuning CLIP to Reason about Pairwise Differences","created":"2024-09-15","cited_by_count":6,"area":"lr"},{"id":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2503.16106","title":"OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2503.18695","title":"OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2506.23822","title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","created":"2025-06-30","cited_by_count":6,"area":"mllm"}],"next_cursor":"100"}