{"total":400,"rows":[{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"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":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371,"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":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202,"area":null},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"id":"2404.16022","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","created":"2024-04-24","cited_by_count":144,"area":null},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138,"area":null},{"id":"2404.00308","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","created":"2024-03-30","cited_by_count":126,"area":null},{"id":"2310.01403","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","created":"2023-10-02","cited_by_count":118,"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":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"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":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"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":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"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":"2308.13234","title":"Decoding Natural Images from EEG for Object Recognition","created":"2023-08-25","cited_by_count":81,"area":null},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81,"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":"2401.02955","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","created":"2024-01-05","cited_by_count":75,"area":null},{"id":"2312.08870","title":"Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens","created":"2023-12-12","cited_by_count":71,"area":null},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"area":null},{"id":"2403.13043","title":"When Do We Not Need Larger Vision Models?","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","cited_by_count":67,"area":null},{"id":"2412.09082","title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method","created":"2024-12-12","cited_by_count":67,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"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":"2312.02153","title":"Aligning and Prompting Everything All at Once for Universal Visual Perception","created":"2023-12-04","cited_by_count":60,"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":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2312.08885","title":"SceneWiz3D: Towards Text-guided 3D Scene Composition","created":"2023-12-13","cited_by_count":54,"area":null},{"id":"2410.10777","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation","created":"2024-10-14","cited_by_count":54,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2411.17991","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","created":"2024-11-27","cited_by_count":47,"area":null},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2405.20204","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","created":"2024-05-30","cited_by_count":46,"area":null},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","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":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","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":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"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":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33,"area":null},{"id":"2312.09128","title":"Tokenize Anything via Prompting","created":"2023-12-14","cited_by_count":31,"area":null},{"id":"2312.00869","title":"Segment and Caption Anything","created":"2023-12-01","cited_by_count":30,"area":null},{"id":"2404.01294","title":"CosmicMan: A Text-to-Image Foundation Model for Humans","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2306.03089","title":"Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models","created":"2023-06-05","cited_by_count":29,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"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":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2407.04106","title":"MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis","created":"2024-07-04","cited_by_count":28,"area":null},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"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":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2405.05237","title":"EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2501.01767","title":"LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction","created":"2025-01-03","cited_by_count":25,"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":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","created":"2024-09-26","cited_by_count":24,"area":null},{"id":"2402.01735","title":"VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models","created":"2024-01-29","cited_by_count":23,"area":null},{"id":"2304.01184","title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation","created":"2023-04-03","cited_by_count":22,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2405.17913","title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null}],"next_cursor":"100"}