{"total":70,"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":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232,"area":"mllm"},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90,"area":"lr"},{"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":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2410.02746","title":"Contrastive Localized Language-Image Pre-Training","created":"2024-10-03","cited_by_count":33,"area":"mllm"},{"id":"2403.07241","title":"Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2410.02098","title":"EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing","created":"2024-10-02","cited_by_count":30,"area":"diffusion"},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2412.03704","title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","created":"2024-12-04","cited_by_count":23,"area":"lr"},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2410.17251","title":"Altogether: Image Captioning via Re-aligning Alt-text","created":"2024-10-22","cited_by_count":17,"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":"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":"2412.00440","title":"Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training","created":"2024-11-30","cited_by_count":13,"area":"mllm"},{"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":"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":"2510.03519","title":"TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"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":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"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":"2506.21233","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","created":"2025-06-26","cited_by_count":9,"area":null},{"id":"2603.09160","title":"RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning","created":"2026-03-10","cited_by_count":9,"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":"2503.12303","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","created":"2025-03-16","cited_by_count":7,"area":"synth"},{"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":"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":"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":"2412.17417","title":"Synth-Align: Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment","created":"2024-12-23","cited_by_count":6,"area":"mllm"},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2409.15125","title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation","created":"2024-09-23","cited_by_count":4,"area":"mllm"},{"id":"2501.04155","title":"MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation","created":"2025-01-07","cited_by_count":4,"area":"mllm"},{"id":"2505.22613","title":"RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2512.14480","title":"SuperCLIP: CLIP with Simple Classification Supervision","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2410.08211","title":"LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts","created":"2024-10-10","cited_by_count":3,"area":"mllm"},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2510.20095","title":"BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2503.06626","title":"DiffCLIP: Differential Attention Meets CLIP","created":"2025-03-09","cited_by_count":2,"area":"mllm"},{"id":"2503.14559","title":"Squeeze Out Tokens from Sample for Finer-Grained Data Governance","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2507.19362","title":"LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences","created":"2025-07-25","cited_by_count":2,"area":"mllm"},{"id":"2511.04080","title":"Caption Injection for Optimization in Generative Search Engine","created":"2025-11-06","cited_by_count":2,"area":"rag"},{"id":"2512.11141","title":"Learning complete and explainable visual representations from itemized text supervision","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.13886","title":"Revisiting Multi-Task Visual Representation Learning","created":"2026-01-20","cited_by_count":2,"area":"mllm"},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2605.11405","title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","created":"2026-05-12","cited_by_count":2,"area":"mllm"},{"id":"2412.04429","title":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition","created":"2024-12-05","cited_by_count":1,"area":"mllm"},{"id":"2505.08818","title":"Position: Restructuring of Categories and Implementation of Guidelines Essential for VLM Adoption in Healthcare","created":"2025-05-12","cited_by_count":1,"area":"mllm"},{"id":"2507.14024","title":"Moodifier: MLLM-Enhanced Emotion-Driven Image Editing","created":"2025-07-18","cited_by_count":1,"area":"mllm"},{"id":"2508.17497","title":"Multimodal Representation Learning Conditioned on Semantic Relations","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2511.23170","title":"PowerCLIP: Powerset Alignment for Contrastive Pre-Training","created":"2025-11-28","cited_by_count":1,"area":"mllm"},{"id":"2602.23351","title":"Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2507.18915","title":"Mining Contextualized Visual Associations from Images for Creativity Understanding","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2511.05057","title":"Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data Approach","created":"2025-11-07","cited_by_count":0,"area":"synth"},{"id":"2511.20274","title":"SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2601.21426","title":"MultiModal Fine-tuning with Synthetic Captions","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.02767","title":"ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.12498","title":"Lit2Vec: A Reproducible Workflow for Building a Legally Screened Chemistry Corpus from S2ORC for Downstream Retrieval and Text Mining","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2606.13275","title":"Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.00858","title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.11692","title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.25575","title":"MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2610.17866","title":"MicroCLIP: Connecting Text and Microscopy Images via Contrastive Language--Image Pretraining","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}