{"total":835,"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":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062,"area":null},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777,"area":null},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"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":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"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":"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":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"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":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"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":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274,"area":null},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"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":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"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":"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":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"area":null},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172,"area":null},{"id":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171,"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":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166,"area":null},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"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":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2406.04882","title":"InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment","created":"2024-06-07","cited_by_count":157,"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":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"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":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142,"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":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140,"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":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"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":"2310.12798","title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","created":"2023-10-19","cited_by_count":128,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"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":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118,"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":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110,"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":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"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":"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":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","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":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2410.05260","title":"DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control","created":"2024-10-07","cited_by_count":84,"area":null},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"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":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2407.04172","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","created":"2024-07-04","cited_by_count":79,"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":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","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":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","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":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","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":"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":"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":"2406.04292","title":"VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval","created":"2024-06-06","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":"2401.13923","title":"Towards 3D Molecule-Text Interpretation in Language Models","created":"2024-01-25","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":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2412.04332","title":"Liquid: Language Models are Scalable and Unified Multi-modal Generators","created":"2024-12-05","cited_by_count":63,"area":null}],"next_cursor":"100"}