{"total":1331,"rows":[{"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":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"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":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"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":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503,"area":null},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"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":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"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":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363,"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":"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":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286,"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":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"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":"2412.08629","title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models","created":"2024-12-11","cited_by_count":217,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"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":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202,"area":null},{"id":"2403.17834","title":"Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","created":"2024-03-26","cited_by_count":199,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179,"area":null},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"area":null},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"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":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"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":"2406.04449","title":"MAIRA-2: Grounded Radiology Report Generation","created":"2024-06-06","cited_by_count":145,"area":null},{"id":"2311.07574","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","created":"2023-11-13","cited_by_count":144,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132,"area":null},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2401.02330","title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model","created":"2024-01-04","cited_by_count":129,"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":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"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":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"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":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"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":"2405.04007","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","created":"2024-05-07","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":"2401.18084","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","created":"2024-01-31","cited_by_count":95,"area":null},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2405.03162","title":"Advancing Multimodal Medical Capabilities of Gemini","created":"2024-05-06","cited_by_count":90,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87,"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":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","cited_by_count":87,"area":null},{"id":"2311.16208","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","created":"2023-11-27","cited_by_count":86,"area":null},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86,"area":null},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"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":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82,"area":null},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82,"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":"2405.19092","title":"Benchmarking and Improving Detail Image Caption","created":"2024-05-29","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":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","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":"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":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72,"area":null},{"id":"2405.03003","title":"Parameter-Efficient Fine-Tuning with Discrete Fourier Transform","created":"2024-05-05","cited_by_count":71,"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":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70,"area":null},{"id":"2402.13232","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","created":"2024-02-20","cited_by_count":69,"area":null},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69,"area":null},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67,"area":null},{"id":"2403.13043","title":"When Do We Not Need Larger Vision Models?","created":"2024-03-19","cited_by_count":67,"area":null}],"next_cursor":"100"}