{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"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":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"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":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"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":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59},{"id":"2512.07237","title":"Unified Camera Positional Encoding for Controlled Video Generation","created":"2025-12-08","cited_by_count":37},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25},{"id":"2510.20385","title":"Positional Encoding Field","created":"2025-10-23","cited_by_count":20},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19},{"id":"2512.05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation","created":"2025-12-04","cited_by_count":14},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8}],"next_cursor":null}