{"total":229,"rows":[{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261,"area":"wm"},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501,"area":"agents"},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366,"area":"diffusion"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2510.18234","title":"DeepSeek-OCR: Contexts Optical Compression","created":"2025-10-21","cited_by_count":183,"area":null},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179,"area":"mllm"},{"id":"2502.17422","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","created":"2025-02-24","cited_by_count":176,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"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":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154,"area":null},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151,"area":"diffusion"},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140,"area":null},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138,"area":"moe"},{"id":"2406.18583","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","created":"2024-06-05","cited_by_count":132,"area":"diffusion"},{"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":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113,"area":"diffusion"},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2504.07963","title":"PixelFlow: Pixel-Space Generative Models with Flow","created":"2025-04-10","cited_by_count":97,"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":"2402.12376","title":"FiT: Flexible Vision Transformer for Diffusion Model","created":"2024-02-19","cited_by_count":85,"area":"diffusion"},{"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":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","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":"2509.01563","title":"Kwai Keye-VL 1.5 Technical Report","created":"2025-09-01","cited_by_count":73,"area":"mllm"},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71,"area":null},{"id":"2501.04698","title":"ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning","created":"2025-01-08","cited_by_count":68,"area":"diffusion"},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67,"area":"diffusion"},{"id":"2506.23044","title":"Ovis-U1 Technical Report","created":"2025-06-29","cited_by_count":67,"area":null},{"id":"2501.01320","title":"SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration","created":"2025-01-02","cited_by_count":62,"area":"diffusion"},{"id":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","cited_by_count":57,"area":null},{"id":"2506.05083","title":"SeedEdit 3.0: Fast and High-Quality Generative Image Editing","created":"2025-06-05","cited_by_count":53,"area":null},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2507.01949","title":"Kwai Keye-VL Technical Report","created":"2025-07-02","cited_by_count":47,"area":"mllm"},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"area":"mllm"},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43,"area":null},{"id":"2412.09856","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","created":"2024-12-13","cited_by_count":43,"area":"diffusion"},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2509.01215","title":"POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion","created":"2025-09-01","cited_by_count":34,"area":"mllm"},{"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":"2501.05179","title":"Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models","created":"2025-01-09","cited_by_count":32,"area":"mllm"},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2407.03791","title":"M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks","created":"2024-07-04","cited_by_count":27,"area":"mllm"},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2405.13226","title":"Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum","created":"2024-05-21","cited_by_count":26,"area":null},{"id":"2403.18361","title":"ViTAR: Vision Transformer with Any Resolution","created":"2024-03-27","cited_by_count":25,"area":null},{"id":"2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","created":"2024-09-26","cited_by_count":24,"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":"2606.14409","title":"Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack","created":"2026-06-12","cited_by_count":22,"area":"vla"},{"id":"2501.03120","title":"CAT: Content-Adaptive Image Tokenization","created":"2025-01-06","cited_by_count":21,"area":null},{"id":"2606.03264","title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","created":"2026-06-02","cited_by_count":21,"area":null},{"id":"2410.01359","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","created":"2024-10-02","cited_by_count":20,"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":"2604.07430","title":"HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents","created":"2026-04-08","cited_by_count":18,"area":"agents"},{"id":"2504.14692","title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","created":"2025-04-20","cited_by_count":17,"area":"mllm"},{"id":"2401.16741","title":"MESA: Matching Everything by Segmenting Anything","created":"2024-01-30","cited_by_count":16,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"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":"2410.13925","title":"FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model","created":"2024-10-17","cited_by_count":15,"area":"diffusion"},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2504.04708","title":"SapiensID: Foundation for Human Recognition","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2509.23344","title":"DentVLM: A Multimodal Vision-Language Model for Comprehensive Dental Diagnosis and Enhanced Clinical Practice","created":"2025-09-27","cited_by_count":14,"area":"mllm"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2411.16173","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","created":"2024-11-25","cited_by_count":13,"area":"mllm"},{"id":"2505.02471","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2508.20279","title":"How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding","created":"2025-08-27","cited_by_count":13,"area":"lr"},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13,"area":null},{"id":"2310.00632","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","created":"2023-10-01","cited_by_count":12,"area":null},{"id":"2502.20126","title":"FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute","created":"2025-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2405.18616","title":"Wavelet-Based Image Tokenizer for Vision Transformers","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2505.24158","title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders","created":"2025-05-30","cited_by_count":10,"area":"mllm"},{"id":"2603.13394","title":"Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models","created":"2026-03-11","cited_by_count":10,"area":"mllm"},{"id":"2410.02179","title":"HATFormer: Historic Handwritten Arabic Text Recognition with Transformers","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2509.15496","title":"Lynx: Towards High-Fidelity Personalized Video Generation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2510.22946","title":"LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2402.05424","title":"Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures","created":"2024-02-08","cited_by_count":8,"area":null},{"id":"2408.08822","title":"PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores","created":"2024-08-16","cited_by_count":8,"area":"diffusion"},{"id":"2501.15415","title":"OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery","created":"2025-01-26","cited_by_count":8,"area":null},{"id":"2503.24180","title":"Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2508.04825","title":"Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off","created":"2025-08-06","cited_by_count":8,"area":"diffusion"},{"id":"2604.04634","title":"Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale","created":"2026-04-06","cited_by_count":8,"area":null},{"id":"2607.12894","title":"Hy-Embodied-VLM-1.0: Efficient Physical-World Agents","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2402.15307","title":"Representing Online Handwriting for Recognition in Large Vision-Language Models","created":"2024-02-23","cited_by_count":7,"area":"mllm"}],"next_cursor":"100"}