{"total":93,"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":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107,"area":"lr"},{"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":"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":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83,"area":"mllm"},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77,"area":"mllm"},{"id":"2310.13828","title":"Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":75,"area":"safety"},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"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":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70,"area":"mllm"},{"id":"2510.02912","title":"Don't Just Chase \"Highlighted Tokens\" in MLLMs: Revisiting Visual Holistic Context Retention","created":"2025-10-03","cited_by_count":47,"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":"2310.16656","title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation","created":"2023-10-25","cited_by_count":41,"area":"diffusion"},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2310.02110","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","created":"2023-10-03","cited_by_count":33,"area":"mllm"},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2503.11509","title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","created":"2025-03-14","cited_by_count":24,"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":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20,"area":"mllm"},{"id":"2405.19547","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","created":"2024-05-29","cited_by_count":20,"area":"mllm"},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","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":"2410.17251","title":"Altogether: Image Captioning via Re-aligning Alt-text","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2310.16825","title":"CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images","created":"2023-10-25","cited_by_count":16,"area":"diffusion"},{"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":"2405.16915","title":"Multilingual Diversity Improves Vision-Language Representations","created":"2024-05-27","cited_by_count":14,"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":"2409.19425","title":"Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment","created":"2024-09-28","cited_by_count":12,"area":"mllm"},{"id":"2312.06112","title":"MAFA: Managing False Negatives for Vision-Language Pre-training","created":"2023-12-11","cited_by_count":11,"area":"mllm"},{"id":"2411.05195","title":"Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder","created":"2024-11-07","cited_by_count":11,"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":"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":"2307.11315","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","created":"2023-07-21","cited_by_count":8,"area":"mllm"},{"id":"2310.14356","title":"Semantic and Expressive Variation in Image Captions Across Languages","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2311.08400","title":"Towards Open-Ended Visual Recognition with Large Language Model","created":"2023-11-14","cited_by_count":8,"area":null},{"id":"2504.01735","title":"AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2602.21655","title":"CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning","created":"2026-02-25","cited_by_count":8,"area":"alignment"},{"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":"2407.00102","title":"Curriculum Learning with Quality-Driven Data Selection","created":"2024-06-27","cited_by_count":7,"area":"mllm"},{"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":"2410.06777","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","created":"2024-10-09","cited_by_count":7,"area":"mllm"},{"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":"2502.09598","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":"2509.19212","title":"Steering Multimodal Large Language Models Decoding for Context-Aware Safety","created":"2025-09-23","cited_by_count":7,"area":"mllm"},{"id":"2402.02055","title":"Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning","created":"2024-02-03","cited_by_count":6,"area":"mllm"},{"id":"2404.14409","title":"CrossScore: Towards Multi-View Image Evaluation and Scoring","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2407.20756","title":"SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models","created":"2024-07-30","cited_by_count":6,"area":"mllm"},{"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":"2411.08664","title":"UniMat: Unifying Materials Embeddings through Multi-modal Learning","created":"2024-11-13","cited_by_count":6,"area":null},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2401.15896","title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","created":"2024-01-29","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":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2411.17489","title":"Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions","created":"2024-11-26","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":"2507.22828","title":"CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models","created":"2025-07-30","cited_by_count":3,"area":"mllm"},{"id":"2511.08917","title":"\"It's trained by non-disabled people\": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models","created":"2025-11-12","cited_by_count":3,"area":"mllm"},{"id":"2311.17898","title":"Contextual Knowledge Pursuit for Faithful Visual Synthesis","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2410.16166","title":"Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining","created":"2024-10-21","cited_by_count":2,"area":"mllm"},{"id":"2411.10252","title":"Visual-Linguistic Agent: Towards Collaborative Contextual Object Reasoning","created":"2024-11-15","cited_by_count":2,"area":"lr"},{"id":"2503.18407","title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP","created":"2025-03-24","cited_by_count":2,"area":"mllm"},{"id":"2507.13568","title":"LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2510.06973","title":"Addressing the ID-Matching Challenge in Long Video Captioning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2505.22627","title":"Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.21874","title":"On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling","created":"2025-06-27","cited_by_count":1,"area":"mllm"},{"id":"2507.09256","title":"Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2510.06820","title":"Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.19892","title":"Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities","created":"2025-10-22","cited_by_count":1,"area":"mllm"},{"id":"2512.03173","title":"Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping","created":"2025-12-02","cited_by_count":1,"area":null},{"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":"2604.16979","title":"DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models","created":"2026-04-18","cited_by_count":1,"area":"mllm"},{"id":"2606.14277","title":"One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs","created":"2026-06-12","cited_by_count":1,"area":"mllm"},{"id":"2403.01306","title":"ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2503.04842","title":"Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2504.03153","title":"MORAL: A Multimodal Reinforcement Learning Framework for Decision Making in Autonomous Laboratories","created":"2025-04-04","cited_by_count":0,"area":"deeprl"},{"id":"2507.08575","title":"Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing","created":"2025-07-11","cited_by_count":0,"area":"mllm"},{"id":"2507.08590","title":"Visual Semantic Description Generation with MLLMs for Image-Text Matching","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2507.18311","title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","created":"2025-07-24","cited_by_count":0,"area":"mllm"},{"id":"2512.14230","title":"Understanding the Gain from Data Filtering in Multimodal Contrastive Learning","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.06451","title":"BrokenBind: Universal Modality Exploration beyond Dataset Boundaries","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.16918","title":"Xray-Visual Models: Scaling Vision models on Industry Scale Data","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.27932","title":"Dynamic Cluster Data Sampling for Efficient and Long-Tail-Aware Vision-Language Pre-training","created":"2026-04-30","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":"2609.17868","title":"Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology","created":"2026-09-15","cited_by_count":0,"area":"mllm"}],"next_cursor":null}