{"list":"other","total":59,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"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},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"id":"2501.06336","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","created":"2025-01-10","cited_by_count":95},{"id":"2503.06287","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","created":"2025-03-08","cited_by_count":83},{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39},{"id":"2510.10903","title":"Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey","created":"2025-10-13","cited_by_count":32},{"id":"2408.08000","title":"MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing","created":"2024-08-15","cited_by_count":30},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29},{"id":"2505.03673","title":"RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration","created":"2025-05-06","cited_by_count":28},{"id":"2412.14592","title":"Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties","created":"2024-12-19","cited_by_count":26},{"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},{"id":"2411.00781","title":"Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies","created":"2024-10-16","cited_by_count":19},{"id":"2312.04554","title":"Improved Visual Grounding through Self-Consistent Explanations","created":"2023-12-07","cited_by_count":17},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17},{"id":"2502.18373","title":"EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity","created":"2025-02-25","cited_by_count":15},{"id":"2312.04670","title":"Rapid Motor Adaptation for Robotic Manipulator Arms","created":"2023-12-07","cited_by_count":14},{"id":"2504.04956","title":"REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning","created":"2025-04-07","cited_by_count":14},{"id":"2503.21457","title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","created":"2025-03-27","cited_by_count":12},{"id":"2507.19239","title":"CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception","created":"2025-07-25","cited_by_count":12},{"id":"2410.01544","title":"Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension","created":"2024-10-02","cited_by_count":10},{"id":"2501.12263","title":"mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework","created":"2025-01-21","cited_by_count":9},{"id":"2510.26536","title":"RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration","created":"2025-10-30","cited_by_count":9},{"id":"2503.08421","title":"Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels","created":"2025-03-11","cited_by_count":7},{"id":"2411.08753","title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","created":"2024-11-13","cited_by_count":6},{"id":"2510.03701","title":"Referring Expression Comprehension for Small Objects","created":"2025-10-04","cited_by_count":6},{"id":"2510.00483","title":"MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzles","created":"2025-10-01","cited_by_count":5},{"id":"2406.13865","title":"SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking","created":"2024-06-19","cited_by_count":4},{"id":"2508.03266","title":"EgoPrompt: Prompt Learning for Egocentric Action Recognition","created":"2025-08-05","cited_by_count":4}],"next_cursor":null}