{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"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":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2404.07191","title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","created":"2024-04-10","cited_by_count":433},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"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":"2004.01803","title":"SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation","created":"2020-04-03","cited_by_count":170},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92},{"id":"2408.00653","title":"SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement","created":"2024-08-01","cited_by_count":65},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48},{"id":"2507.23478","title":"3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding","created":"2025-07-31","cited_by_count":47},{"id":"2105.10382","title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","created":"2021-05-21","cited_by_count":42},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42},{"id":"2509.10884","title":"Nav-R1: Reasoning and Navigation in Embodied Scenes","created":"2025-09-13","cited_by_count":38},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32},{"id":"2505.23734","title":"ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS","created":"2025-05-29","cited_by_count":32},{"id":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28},{"id":"2503.16302","title":"Unleashing Vecset Diffusion Model for Fast Shape Generation","created":"2025-03-20","cited_by_count":26},{"id":"2407.10061","title":"InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation","created":"2024-07-14","cited_by_count":23},{"id":"2405.11286","title":"Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion","created":"2024-05-18","cited_by_count":19},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19},{"id":"2411.06481","title":"KMM: Key Frame Mask Mamba for Extended Motion Generation","created":"2024-11-10","cited_by_count":16},{"id":"2505.15232","title":"DC-Scene: Data-Centric Learning for 3D Scene Understanding","created":"2025-05-21","cited_by_count":15},{"id":"2510.15264","title":"DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion","created":"2025-10-17","cited_by_count":15},{"id":"2504.09518","title":"3D CoCa: Contrastive Learners are 3D Captioners","created":"2025-04-13","cited_by_count":13},{"id":"2410.00890","title":"Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation","created":"2024-10-01","cited_by_count":12},{"id":"2506.10353","title":"Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding","created":"2025-06-12","cited_by_count":9},{"id":"2601.05172","title":"CoV: Chain-of-View Prompting for Spatial Reasoning","created":"2026-01-08","cited_by_count":9},{"id":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6},{"id":"2510.04479","title":"VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery","created":"2025-10-06","cited_by_count":4},{"id":"2512.06424","title":"DragMesh: Interactive 3D Generation Made Easy","created":"2025-12-06","cited_by_count":3},{"id":"2601.06496","title":"3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence","created":"2026-01-10","cited_by_count":3},{"id":"2602.11769","title":"Light4D: Training-Free Extreme Viewpoint 4D Video Relighting","created":"2026-02-12","cited_by_count":2},{"id":"2602.17033","title":"PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing","created":"2026-02-19","cited_by_count":1}],"next_cursor":null}