{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"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":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117},{"id":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","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":"2411.02293","title":"Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation","created":"2024-11-04","cited_by_count":82},{"id":"2007.07627","title":"Fast and Robust Iterative Closest Point","created":"2020-07-15","cited_by_count":67},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54},{"id":"2405.17176","title":"DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models","created":"2024-05-27","cited_by_count":50},{"id":"2403.09675","title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","created":"2024-02-05","cited_by_count":45},{"id":"2411.09823","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","created":"2024-11-14","cited_by_count":38},{"id":"2406.03866","title":"LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model","created":"2024-06-06","cited_by_count":34},{"id":"2411.15138","title":"Material Anything: Generating Materials for Any 3D Object via Diffusion","created":"2024-11-22","cited_by_count":31},{"id":"2503.18476","title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","created":"2025-03-24","cited_by_count":29},{"id":"2503.10289","title":"MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion","created":"2025-03-13","cited_by_count":28},{"id":"2309.12188","title":"SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs","created":"2023-09-21","cited_by_count":24},{"id":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24},{"id":"2008.07817","title":"Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph","created":"2020-08-18","cited_by_count":19},{"id":"2502.05874","title":"MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation","created":"2025-02-09","cited_by_count":19},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17},{"id":"2505.04656","title":"MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation","created":"2025-05-07","cited_by_count":5}],"next_cursor":null}