{"total":167,"rows":[{"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":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"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":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"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":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74,"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":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61,"area":null},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54,"area":null},{"id":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51,"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":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"area":null},{"id":"2412.09604","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","created":"2024-12-12","cited_by_count":42,"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":"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":"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":"2503.01342","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2502.13759","title":"Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework","created":"2025-02-19","cited_by_count":24,"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":"2412.09362","title":"Falcon-UI: Understanding GUI Before Following User Instructions","created":"2024-12-12","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":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2409.19058","title":"CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting","created":"2024-09-27","cited_by_count":20,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","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":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2508.17608","title":"ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning","created":"2025-08-25","cited_by_count":16,"area":null},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15,"area":null},{"id":"2406.05343","title":"M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark","created":"2024-06-08","cited_by_count":14,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2506.14028","title":"MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2411.11360","title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","created":"2024-11-18","cited_by_count":13,"area":null},{"id":"2411.17261","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","created":"2024-11-26","cited_by_count":13,"area":null},{"id":"2504.09255","title":"FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment","created":"2025-04-12","cited_by_count":13,"area":null},{"id":"2504.21308","title":"AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images","created":"2025-04-30","cited_by_count":13,"area":null},{"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":"2412.07147","title":"MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation","created":"2024-12-10","cited_by_count":12,"area":null},{"id":"2501.01243","title":"Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2510.11549","title":"ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?","created":"2025-10-13","cited_by_count":12,"area":null},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12,"area":null},{"id":"2503.24267","title":"FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics","created":"2025-03-31","cited_by_count":11,"area":null},{"id":"2512.00752","title":"Charts Are Not Images: On the Challenges of Scientific Chart Editing","created":"2025-11-30","cited_by_count":11,"area":null},{"id":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2503.05543","title":"Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information","created":"2025-03-07","cited_by_count":10,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2510.16641","title":"MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models","created":"2025-10-18","cited_by_count":10,"area":null},{"id":"2410.04345","title":"MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?","created":"2024-10-06","cited_by_count":9,"area":null},{"id":"2507.21167","title":"ChartM$^3$: Benchmarking Chart Editing with Multimodal Instructions","created":"2025-07-25","cited_by_count":9,"area":null},{"id":"2602.05998","title":"VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2408.14158","title":"Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2508.12291","title":"RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts","created":"2025-08-17","cited_by_count":8,"area":null},{"id":"2509.11860","title":"MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues","created":"2025-09-15","cited_by_count":8,"area":null},{"id":"2411.14823","title":"Omni-IML: Towards Unified Image Manipulation Localization","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2503.01115","title":"WeGen: A Unified Model for Interactive Multimodal Generation as We Chat","created":"2025-03-03","cited_by_count":7,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2502.20420","title":"Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.00624","title":"An evaluation of DeepSeek Models in Biomedical Natural Language Processing","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2505.18570","title":"VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2506.14642","title":"3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2602.00854","title":"Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2411.11507","title":"SignEye: Traffic Sign Interpretation from Vehicle First-Person View","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2412.04774","title":"Foundation Models for Low-Resource Language Education (Vision Paper)","created":"2024-12-06","cited_by_count":5,"area":null},{"id":"2502.08168","title":"SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2504.17213","title":"MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding","created":"2025-04-24","cited_by_count":5,"area":null},{"id":"2505.18660","title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2511.14259","title":"ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2605.15735","title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","created":"2026-05-15","cited_by_count":5,"area":null},{"id":"2506.08002","title":"Aligning Text, Images, and 3D Structure Token-by-Token","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2506.13888","title":"VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2404.10757","title":"Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2503.18681","title":"Commander-GPT: Fully Unleashing the Sarcasm Detection Capability of Multi-Modal Large Language Models","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2504.18406","title":"HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2505.11945","title":"Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2507.16213","title":"Advancing Visual Large Language Model for Multi-granular Versatile Perception","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2509.23841","title":"Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2602.19944","title":"Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2602.21956","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2603.00461","title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2604.10789","title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.01638","title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","created":"2026-05-02","cited_by_count":3,"area":null},{"id":"2605.27378","title":"OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.11702","title":"MedCTA: A Benchmark for Clinical Tool Agents","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2410.11068","title":"Character-aware audio-visual subtitling in context","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2411.16824","title":"Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge","created":"2024-11-25","cited_by_count":2,"area":null},{"id":"2502.12799","title":"Towards Text-Image Interleaved Retrieval","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.06029","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2505.23272","title":"Are MLMs Trapped in the Visual Room?","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.01015","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2506.19420","title":"Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.09693","title":"ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments","created":"2025-07-13","cited_by_count":2,"area":null}],"next_cursor":"100"}