{"list":"other","total":57,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2103.12352","title":"iMAP: Implicit Mapping and Positioning in Real-Time","created":"2021-03-23","cited_by_count":476},{"id":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"2008.07519","title":"V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction","created":"2020-08-17","cited_by_count":292},{"id":"2209.12836","title":"Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps","created":"2022-09-26","cited_by_count":255},{"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":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227},{"id":"2306.03083","title":"MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion","created":"2023-06-05","cited_by_count":213},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"2303.00749","title":"S-NeRF: Neural Radiance Fields for Street Views","created":"2023-03-01","cited_by_count":116},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"2201.01389","title":"Semantic Communications: Principles and Challenges","created":"2021-12-30","cited_by_count":91},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76},{"id":"2403.16034","title":"V2X-Real: a Large-Scale Dataset for Vehicle-to-Everything Cooperative Perception","created":"2024-03-24","cited_by_count":66},{"id":"2205.05509","title":"READ: Large-Scale Neural Scene Rendering for Autonomous Driving","created":"2022-05-11","cited_by_count":51},{"id":"2307.14620","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","created":"2023-07-27","cited_by_count":51},{"id":"2308.16714","title":"Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception","created":"2023-08-31","cited_by_count":38},{"id":"2203.10821","title":"Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields","created":"2022-03-21","cited_by_count":29},{"id":"2306.04098","title":"Phoenix: A Federated Generative Diffusion Model","created":"2023-06-07","cited_by_count":22},{"id":"2404.16139","title":"A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges","created":"2024-04-24","cited_by_count":13},{"id":"2403.11460","title":"Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning","created":"2024-03-18","cited_by_count":12},{"id":"2312.09095","title":"ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field","created":"2023-12-14","cited_by_count":11},{"id":"2503.06426","title":"Federated Learning for Diffusion Models","created":"2025-03-09","cited_by_count":7},{"id":"2403.13199","title":"DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images","created":"2024-03-19","cited_by_count":4},{"id":"2404.08490","title":"SemHARQ: Semantic-Aware Hybrid Automatic Repeat Request for Multi-Task Semantic Communications","created":"2024-04-12","cited_by_count":4},{"id":"2502.14891","title":"CoDiff: Conditional Diffusion Model for Collaborative 3D Object Detection","created":"2025-02-17","cited_by_count":4},{"id":"2507.21572","title":"No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering","created":"2025-07-29","cited_by_count":3},{"id":"2409.20289","title":"Distributed NeRF Learning for Collaborative Multi-Robot Perception","created":"2024-09-30","cited_by_count":2},{"id":"2504.21774","title":"Is Intermediate Fusion All You Need for UAV-based Collaborative Perception?","created":"2025-04-30","cited_by_count":1},{"id":"2507.06449","title":"FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models","created":"2025-07-08","cited_by_count":1}],"next_cursor":null}