{"total":58,"rows":[{"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":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"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":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77,"area":null},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67,"area":null},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2502.06734","title":"Se\\~norita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists","created":"2025-02-10","cited_by_count":61,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2411.02336","title":"MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D","created":"2024-11-04","cited_by_count":34,"area":null},{"id":"2412.10439","title":"CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs","created":"2024-12-11","cited_by_count":33,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2503.04720","title":"FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video","created":"2025-03-06","cited_by_count":21,"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":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2510.10921","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model","created":"2025-10-13","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":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2506.04228","title":"LayerFlow: A Unified Model for Layer-aware Video Generation","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2510.14256","title":"Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2412.10342","title":"Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining","created":"2024-12-13","cited_by_count":7,"area":null},{"id":"2501.06184","title":"PEACE: Empowering Geologic Map Holistic Understanding with MLLMs","created":"2025-01-10","cited_by_count":7,"area":null},{"id":"2506.03150","title":"IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2507.01945","title":"LongAnimation: Long Animation Generation with Dynamic Global-Local Memory","created":"2025-07-02","cited_by_count":6,"area":null},{"id":"2412.11906","title":"PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2509.21072","title":"Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2412.20541","title":"SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes","created":"2024-12-29","cited_by_count":4,"area":null},{"id":"2505.22613","title":"RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.17404","title":"MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling","created":"2025-08-24","cited_by_count":4,"area":null},{"id":"2510.25146","title":"EA3D: Online Open-World 3D Object Extraction from Streaming Videos","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2503.03644","title":"DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms","created":"2025-03-05","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":"2605.17360","title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2502.15422","title":"Evaluating Multimodal Generative AI with Korean Educational Standards","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.00330","title":"How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition","created":"2025-03-01","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},{"id":"2508.14405","title":"CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2512.05044","title":"Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2607.06468","title":"EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2410.13891","title":"S$^4$ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2501.01982","title":"Is Your Image a Good Storyteller?","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2508.11486","title":"Automated Building Heritage Assessment Using Street-Level Imagery","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.01610","title":"Improving Large Vision and Language Models by Learning from a Panel of Peers","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2605.26576","title":"TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.26355","title":"Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2608.30935","title":"LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2509.17421","title":"RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2601.02888","title":"RPIQ: Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization for Visually Impaired Assistance","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.05180","title":"MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.14069","title":"Towards Unconstrained Human-Object Interaction","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.21362","title":"KD-CVG: A Knowledge-Driven Approach for Creative Video Generation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.21272","title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2609.08755","title":"Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}