{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"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":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"1905.10711","title":"DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction","created":"2019-05-26","cited_by_count":333},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"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":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2405.14979","title":"CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner","created":"2024-05-23","cited_by_count":123},{"id":"1911.10949","title":"PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes","created":"2019-11-25","cited_by_count":119},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"1711.03129","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","created":"2017-11-08","cited_by_count":108},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74},{"id":"2501.01163","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","created":"2025-01-02","cited_by_count":68},{"id":"1712.02950","title":"CycleGAN, a Master of Steganography","created":"2017-12-08","cited_by_count":65},{"id":"2507.23478","title":"3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding","created":"2025-07-31","cited_by_count":47},{"id":"2212.04386","title":"Multi-View Mesh Reconstruction with Neural Deferred Shading","created":"2022-12-08","cited_by_count":44},{"id":"2509.10884","title":"Nav-R1: Reasoning and Navigation in Embodied Scenes","created":"2025-09-13","cited_by_count":38},{"id":"2510.01623","title":"VLA-R1: Enhancing Reasoning in Vision-Language-Action Models","created":"2025-10-02","cited_by_count":38},{"id":"2407.20892","title":"What is YOLOv5: A deep look into the internal features of the popular object detector","created":"2024-07-30","cited_by_count":37},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32},{"id":"2505.16517","title":"ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models","created":"2025-05-22","cited_by_count":27},{"id":"2308.14078","title":"Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views","created":"2023-08-27","cited_by_count":25},{"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":"2505.15232","title":"DC-Scene: Data-Centric Learning for 3D Scene Understanding","created":"2025-05-21","cited_by_count":15},{"id":"2504.09518","title":"3D CoCa: Contrastive Learners are 3D Captioners","created":"2025-04-13","cited_by_count":13},{"id":"2509.17191","title":"VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery","created":"2025-09-21","cited_by_count":6},{"id":"2410.10927","title":"Cultural Heritage 3D Reconstruction with Diffusion Networks","created":"2024-10-14","cited_by_count":4},{"id":"2412.05203","title":"Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era","created":"2024-12-06","cited_by_count":2}],"next_cursor":null}