{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"2201.08845","title":"Point-NeRF: Point-based Neural Radiance Fields","created":"2022-01-21","cited_by_count":503},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2312.16812","title":"Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis","created":"2023-12-28","cited_by_count":344},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"1906.08240","title":"Neural Point-Based Graphics","created":"2019-06-19","cited_by_count":327},{"id":"2212.05231","title":"NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction","created":"2022-12-10","cited_by_count":314},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2008.05511","title":"Free View Synthesis","created":"2020-08-12","cited_by_count":231},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2402.18668","title":"Simple linear attention language models balance the recall-throughput tradeoff","created":"2024-02-28","cited_by_count":208},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"1506.06825","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","created":"2015-06-22","cited_by_count":185},{"id":"2312.02155","title":"GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis","created":"2023-12-04","cited_by_count":170},{"id":"2403.01444","title":"3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos","created":"2024-03-03","cited_by_count":160},{"id":"2311.17910","title":"HUGS: Human Gaussian Splats","created":"2023-11-29","cited_by_count":154},{"id":"2112.01517","title":"Efficient Neural Radiance Fields for Interactive Free-viewpoint Video","created":"2021-12-02","cited_by_count":150},{"id":"2503.14456","title":"RWKV-7 \"Goose\" with Expressive Dynamic State Evolution","created":"2025-03-18","cited_by_count":141},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99},{"id":"2310.11448","title":"4K4D: Real-Time 4D View Synthesis at 4K Resolution","created":"2023-10-17","cited_by_count":91},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54},{"id":"2502.20220","title":"Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars","created":"2025-02-27","cited_by_count":53},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36},{"id":"2503.16979","title":"Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting","created":"2025-03-21","cited_by_count":36},{"id":"2506.05558","title":"On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images","created":"2025-06-05","cited_by_count":36},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26},{"id":"2206.01649","title":"Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules","created":"2022-06-03","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":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15},{"id":"2602.21204","title":"Test-Time Training with KV Binding Is Secretly Linear Attention","created":"2026-02-24","cited_by_count":13},{"id":"2512.15599","title":"FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision","created":"2025-12-17","cited_by_count":10},{"id":"2505.01838","title":"MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization","created":"2025-05-03","cited_by_count":9},{"id":"2311.16668","title":"LiveNVS: Neural View Synthesis on Live RGB-D Streams","created":"2023-11-28","cited_by_count":6},{"id":"2503.14698","title":"Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting","created":"2025-03-18","cited_by_count":5},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3}],"next_cursor":null}