{"list":"other","total":53,"rows":[{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2306.02224","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","created":"2023-06-04","cited_by_count":255},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"2311.13384","title":"LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes","created":"2023-11-22","cited_by_count":231},{"id":"2309.17288","title":"AutoAgents: A Framework for Automatic Agent Generation","created":"2023-09-29","cited_by_count":216},{"id":"2307.01097","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","created":"2023-07-03","cited_by_count":212},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"2303.17598","title":"Consistent View Synthesis with Pose-Guided Diffusion Models","created":"2023-03-30","cited_by_count":117},{"id":"2304.09667","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","created":"2023-04-19","cited_by_count":117},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2312.06644","title":"AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes","created":"2023-12-11","cited_by_count":82},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76},{"id":"1808.08473","title":"Human-centric Indoor Scene Synthesis Using Stochastic Grammar","created":"2018-08-25","cited_by_count":74},{"id":"2310.03602","title":"Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints","created":"2023-10-05","cited_by_count":60},{"id":"2211.12131","title":"DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models","created":"2022-11-22","cited_by_count":51},{"id":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"2308.10257","title":"Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image","created":"2023-08-20","cited_by_count":19},{"id":"2309.08523","title":"Breathing New Life into 3D Assets with Generative Repainting","created":"2023-09-15","cited_by_count":17},{"id":"1809.10526","title":"Fast and Scalable Position-Based Layout Synthesis","created":"2018-09-27","cited_by_count":16},{"id":"2303.03565","title":"CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding","created":"2023-03-07","cited_by_count":16},{"id":"2306.06212","title":"Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions","created":"2023-06-09","cited_by_count":11}],"next_cursor":null}