{"total":381,"rows":[{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774,"area":null},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"area":null},{"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":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"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":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161,"area":null},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111,"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":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102,"area":null},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99,"area":null},{"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":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"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":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79,"area":null},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"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":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2412.14123","title":"AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities","created":"2024-12-18","cited_by_count":74,"area":null},{"id":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74,"area":null},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2310.14664","title":"Data Pruning via Moving-one-Sample-out","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"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":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51,"area":null},{"id":"2501.07730","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","created":"2025-01-13","cited_by_count":50,"area":null},{"id":"2404.18947","title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","created":"2024-04-27","cited_by_count":49,"area":null},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2402.08831","title":"eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data","created":"2024-02-13","cited_by_count":46,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2310.16226","title":"TiC-CLIP: Continual Training of CLIP Models","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2404.18873","title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2503.20680","title":"Vision as LoRA","created":"2025-03-26","cited_by_count":37,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2310.09562","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","created":"2023-10-14","cited_by_count":35,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"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":"2401.04727","title":"Revisiting Adversarial Training at Scale","created":"2024-01-09","cited_by_count":33,"area":null},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33,"area":null},{"id":"2503.10772","title":"FlowTok: Flowing Seamlessly Across Text and Image Tokens","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","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":"2604.04771","title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","created":"2026-04-06","cited_by_count":27,"area":null},{"id":"2412.17041","title":"An OpenMind for 3D medical vision self-supervised learning","created":"2024-12-22","cited_by_count":26,"area":null},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26,"area":null},{"id":"2306.15658","title":"CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \\$10,000 Budget; An Extra \\$4,000 Unlocks 81.8% Accuracy","created":"2023-06-27","cited_by_count":24,"area":null},{"id":"2404.08639","title":"COCONut: Modernizing COCO Segmentation","created":"2024-04-12","cited_by_count":24,"area":null},{"id":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23,"area":null},{"id":"2406.06973","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2406.10462","title":"CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation","created":"2024-06-15","cited_by_count":23,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2404.16687","title":"NTIRE 2024 Quality Assessment of AI-Generated Content Challenge","created":"2024-04-25","cited_by_count":20,"area":null},{"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":"2309.15954","title":"The Devil is in the Details: A Deep Dive into the Rabbit Hole of Data Filtering","created":"2023-09-27","cited_by_count":19,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"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":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2411.02780","title":"How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion","created":"2024-11-05","cited_by_count":18,"area":null},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18,"area":null},{"id":"2604.11487","title":"NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild","created":"2026-04-13","cited_by_count":18,"area":null},{"id":"2310.05674","title":"Making Scalable Meta Learning Practical","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2406.02547","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","created":"2024-06-04","cited_by_count":17,"area":null}],"next_cursor":"100"}