{"list":"other","total":106,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","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":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2501.14818","title":"Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models","created":"2025-01-20","cited_by_count":70},{"id":"2410.06468","title":"Does Spatial Cognition Emerge in Frontier Models?","created":"2024-10-09","cited_by_count":66},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44},{"id":"2406.10819","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","created":"2024-06-16","cited_by_count":43},{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41},{"id":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38}],"next_cursor":"100"}