{"total":556,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080,"area":null},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733,"area":null},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339,"area":null},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331,"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":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249,"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":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"area":null},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"area":null},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152,"area":null},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148,"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":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"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":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2503.21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","created":"2025-03-27","cited_by_count":96,"area":null},{"id":"2411.09595","title":"LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models","created":"2024-11-14","cited_by_count":91,"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":"2506.07977","title":"OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation","created":"2025-06-09","cited_by_count":87,"area":null},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","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":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","created":"2026-01-28","cited_by_count":74,"area":null},{"id":"2407.08683","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","created":"2024-07-11","cited_by_count":73,"area":null},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62,"area":null},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59,"area":null},{"id":"2407.10943","title":"GRUtopia: Dream General Robots in a City at Scale","created":"2024-07-15","cited_by_count":59,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2411.15245","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","created":"2024-11-22","cited_by_count":53,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2504.04423","title":"UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding","created":"2025-04-06","cited_by_count":49,"area":null},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45,"area":null},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44,"area":null},{"id":"2412.00127","title":"Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads","created":"2024-11-28","cited_by_count":44,"area":null},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2503.14324","title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","created":"2025-03-18","cited_by_count":42,"area":null},{"id":"2410.05440","title":"Can LLMs Understand Time Series Anomalies?","created":"2024-10-07","cited_by_count":41,"area":null},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2405.04940","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","created":"2024-05-08","cited_by_count":39,"area":null},{"id":"2406.03070","title":"A-Bench: Are LMMs Masters at Evaluating AI-generated Images?","created":"2024-06-05","cited_by_count":39,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2504.13176","title":"IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design","created":"2025-04-17","cited_by_count":36,"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":"2403.17008","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","created":"2024-03-25","cited_by_count":31,"area":null},{"id":"2410.02811","title":"SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs","created":"2024-09-22","cited_by_count":31,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2411.16778","title":"GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis","created":"2024-11-25","cited_by_count":29,"area":null},{"id":"2503.10324","title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","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":"2409.00031","title":"Quality Assessment in the Era of Large Models: A Survey","created":"2024-08-17","cited_by_count":26,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2602.11598","title":"ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation","created":"2026-02-12","cited_by_count":25,"area":null},{"id":"2402.11325","title":"ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models","created":"2024-02-17","cited_by_count":24,"area":null},{"id":"2509.09172","title":"Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios","created":"2025-09-11","cited_by_count":24,"area":null},{"id":"2311.07536","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","created":"2023-11-13","cited_by_count":23,"area":null},{"id":"2312.02219","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2502.19870","title":"MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge","created":"2025-02-27","cited_by_count":23,"area":null},{"id":"2503.06470","title":"Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems","created":"2025-03-09","cited_by_count":23,"area":null},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23,"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":"2407.12294","title":"VEON: Vocabulary-Enhanced Occupancy Prediction","created":"2024-07-17","cited_by_count":22,"area":null},{"id":"2412.09362","title":"Falcon-UI: Understanding GUI Before Following User Instructions","created":"2024-12-12","cited_by_count":22,"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":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2408.11319","title":"SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding","created":"2024-08-21","cited_by_count":20,"area":null},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2512.10941","title":"Mull-Tokens: Modality-Agnostic Latent Thinking","created":"2025-12-11","cited_by_count":19,"area":null},{"id":"2406.19263","title":"Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding","created":"2024-06-27","cited_by_count":18,"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},{"id":"2407.11229","title":"Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness","created":"2024-07-15","cited_by_count":17,"area":null},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2503.12689","title":"MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization","created":"2025-03-16","cited_by_count":17,"area":null},{"id":"2506.15569","title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","created":"2025-06-18","cited_by_count":17,"area":null},{"id":"2510.21307","title":"Towards Physically Executable 3D Gaussian for Embodied Navigation","created":"2025-10-24","cited_by_count":17,"area":null},{"id":"2401.06659","title":"WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge","created":"2024-01-12","cited_by_count":16,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2407.01791","title":"{\\mu}-Bench: A Vision-Language Benchmark for Microscopy Understanding","created":"2024-07-01","cited_by_count":15,"area":null}],"next_cursor":"100"}