{"total":82,"rows":[{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"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":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"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":"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":"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":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"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":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"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":"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":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","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":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","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":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56,"area":null},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44,"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":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2403.13164","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2402.16288","title":"PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering","created":"2024-02-26","cited_by_count":34,"area":null},{"id":"2402.19348","title":"Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook","created":"2024-02-29","cited_by_count":33,"area":null},{"id":"2508.04655","title":"X-SAM: From Segment Anything to Any Segmentation","created":"2025-08-06","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":"2409.00031","title":"Quality Assessment in the Era of Large Models: A Survey","created":"2024-08-17","cited_by_count":26,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2312.05476","title":"Exploring the Naturalness of AI-Generated Images","created":"2023-12-09","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":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"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":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"area":null},{"id":"2410.11302","title":"Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs","created":"2024-10-15","cited_by_count":15,"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":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2503.09197","title":"Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting","created":"2025-03-12","cited_by_count":13,"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":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2511.15266","title":"ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing","created":"2025-11-19","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","cited_by_count":10,"area":null},{"id":"2406.07543","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2410.02505","title":"Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2503.09091","title":"Multi-Modal Foundation Models for Computational Pathology: A Survey","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2509.19768","title":"CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition","created":"2025-09-24","cited_by_count":9,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2506.06301","title":"Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review","created":"2025-05-19","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":"2402.07116","title":"Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs","created":"2024-02-11","cited_by_count":7,"area":null},{"id":"2408.07037","title":"PathInsight: Instruction Tuning of Multimodal Datasets and Models for Intelligence Assisted Diagnosis in Histopathology","created":"2024-08-13","cited_by_count":6,"area":null},{"id":"2410.02729","title":"Unified Multimodal Interleaved Document Representation for Retrieval","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2504.01655","title":"Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2412.07405","title":"MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2512.22208","title":"Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2601.21694","title":"ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2502.16175","title":"Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2505.13788","title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2511.13283","title":"TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.10652","title":"TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2406.03728","title":"Evaluating Durability: Benchmark Insights into Multimodal Watermarking","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2407.19178","title":"Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection","created":"2024-07-27","cited_by_count":3,"area":null},{"id":"2508.01237","title":"SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2509.14671","title":"TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2505.18115","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2509.11589","title":"MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2606.05749","title":"MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2601.19247","title":"TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2605.24553","title":"IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2506.21011","title":"Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2511.16908","title":"Q-REAL: Towards Realism and Plausibility Evaluation for AI-Generated Content","created":"2025-11-21","cited_by_count":0,"area":null}],"next_cursor":null}