{"list":"other","total":72,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"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":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"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":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446},{"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":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210},{"id":"2402.11684","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","created":"2024-02-18","cited_by_count":205},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2204.02174","title":"Multi-View Transformer for 3D Visual Grounding","created":"2022-04-05","cited_by_count":140},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"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":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89},{"id":"2412.06673","title":"ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance","created":"2024-12-09","cited_by_count":64},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54},{"id":"2405.19335","title":"X-VILA: Cross-Modality Alignment for Large Language Model","created":"2024-05-29","cited_by_count":46},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27},{"id":"2410.01680","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","created":"2024-10-02","cited_by_count":21},{"id":"2409.04095","title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","created":"2024-09-06","cited_by_count":12},{"id":"2502.16025","title":"FeatSharp: Your Vision Model Features, Sharper","created":"2025-02-22","cited_by_count":6}],"next_cursor":null}