{"list":"other","total":127,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2311.12198","title":"PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics","created":"2023-11-20","cited_by_count":377},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2312.14937","title":"SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes","created":"2023-12-04","cited_by_count":347},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"1910.00935","title":"DiffTaichi: Differentiable Programming for Physical Simulation","created":"2019-10-01","cited_by_count":258},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2401.16663","title":"VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality","created":"2024-01-30","cited_by_count":179},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2311.16037","title":"GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions","created":"2023-11-27","cited_by_count":168},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2303.05512","title":"PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification","created":"2023-03-09","cited_by_count":154},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2001.07457","title":"Learning to Control PDEs with Differentiable Physics","created":"2020-01-21","cited_by_count":132},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109},{"id":"2311.01017","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","created":"2023-11-02","cited_by_count":106},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2104.03311","title":"PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics","created":"2021-04-07","cited_by_count":103},{"id":"2303.12218","title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","created":"2023-03-21","cited_by_count":101},{"id":"2403.09434","title":"Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians","created":"2024-03-14","cited_by_count":97},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97},{"id":"2409.03272","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","created":"2024-09-05","cited_by_count":83},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76},{"id":"2303.13450","title":"Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes","created":"2023-03-23","cited_by_count":75},{"id":"2007.02168","title":"Scalable Differentiable Physics for Learning and Control","created":"2020-07-04","cited_by_count":73},{"id":"2502.11831","title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","created":"2025-02-17","cited_by_count":70},{"id":"2501.18982","title":"OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation","created":"2025-01-31","cited_by_count":69},{"id":"1809.05068","title":"Learning Shape Priors for Single-View 3D Completion and Reconstruction","created":"2018-09-13","cited_by_count":68},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65},{"id":"2303.13843","title":"CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout","created":"2023-03-24","cited_by_count":57},{"id":"2309.15596","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","created":"2023-09-27","cited_by_count":56},{"id":"2312.08885","title":"SceneWiz3D: Towards Text-guided 3D Scene Composition","created":"2023-12-13","cited_by_count":54},{"id":"2103.16021","title":"Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact","created":"2021-03-30","cited_by_count":52},{"id":"2311.13099","title":"PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF","created":"2023-11-22","cited_by_count":51},{"id":"2210.12352","title":"NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos","created":"2022-10-22","cited_by_count":50},{"id":"2210.09420","title":"Differentiable Physics Simulation of Dynamics-Augmented Neural Objects","created":"2022-10-17","cited_by_count":45},{"id":"2203.17275","title":"DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools","created":"2022-03-31","cited_by_count":44},{"id":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43},{"id":"2312.00583","title":"DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation","created":"2023-11-30","cited_by_count":42},{"id":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42},{"id":"2303.02346","title":"FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation","created":"2023-03-04","cited_by_count":40},{"id":"2405.20510","title":"Physically Compatible 3D Object Modeling from a Single Image","created":"2024-05-30","cited_by_count":39},{"id":"2401.15318","title":"Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering","created":"2024-01-27","cited_by_count":37},{"id":"2405.05173","title":"A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective","created":"2024-05-08","cited_by_count":37},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32},{"id":"2411.12789","title":"Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting","created":"2024-11-19","cited_by_count":32},{"id":"2503.21765","title":"Exploring the Evolution of Physics Cognition in Video Generation: A Survey","created":"2025-03-27","cited_by_count":31}],"next_cursor":"100"}