{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2201.01266","title":"Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images","created":"2022-01-04","cited_by_count":830},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"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":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"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":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2104.04532","title":"Neural RGB-D Surface Reconstruction","created":"2021-04-09","cited_by_count":313},{"id":"2412.04467","title":"VisionZip: Longer is Better but Not Necessary in Vision Language Models","created":"2024-12-05","cited_by_count":313},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2409.06765","title":"gsplat: An Open-Source Library for Gaussian Splatting","created":"2024-09-10","cited_by_count":285},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2007.09451","title":"Feature Pyramid Transformer","created":"2020-07-18","cited_by_count":96},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19},{"id":"2510.18775","title":"UltraGen: High-Resolution Video Generation with Hierarchical Attention","created":"2025-10-21","cited_by_count":18},{"id":"2210.08457","title":"Scratching Visual Transformer's Back with Uniform Attention","created":"2022-10-16","cited_by_count":16},{"id":"2411.16680","title":"Quark: Real-time, High-resolution, and General Neural View Synthesis","created":"2024-11-25","cited_by_count":16},{"id":"2310.12442","title":"Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer","created":"2023-10-19","cited_by_count":13},{"id":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6},{"id":"2501.17978","title":"VoD-3DGS: View-opacity-Dependent 3D Gaussian Splatting","created":"2025-01-29","cited_by_count":5},{"id":"2507.08776","title":"CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering","created":"2025-07-11","cited_by_count":5},{"id":"2509.06950","title":"Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data","created":"2025-09-08","cited_by_count":4}],"next_cursor":null}