{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2505.08617","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","created":"2025-05-13","cited_by_count":163},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2505.19255","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","created":"2025-05-25","cited_by_count":90},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76},{"id":"2302.01330","title":"SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections","created":"2023-02-02","cited_by_count":72},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70},{"id":"2301.09637","title":"InfiniCity: Infinite-Scale City Synthesis","created":"2023-01-23","cited_by_count":68},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67},{"id":"2503.18470","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","created":"2025-03-24","cited_by_count":51},{"id":"2303.13515","title":"Persistent Nature: A Generative Model of Unbounded 3D Worlds","created":"2023-03-23","cited_by_count":44},{"id":"2505.20289","title":"VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection","created":"2025-05-26","cited_by_count":34},{"id":"2302.06826","title":"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models","created":"2023-02-14","cited_by_count":33},{"id":"2503.16420","title":"SynCity: Training-Free Generation of 3D Worlds","created":"2025-03-20","cited_by_count":31},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28},{"id":"2406.04983","title":"CityCraft: A Real Crafter for 3D City Generation","created":"2024-06-07","cited_by_count":26},{"id":"2312.01508","title":"CityGen: Infinite and Controllable City Layout Generation","created":"2023-12-03","cited_by_count":22},{"id":"2502.05874","title":"MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation","created":"2025-02-09","cited_by_count":19},{"id":"2503.16375","title":"NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes","created":"2025-03-20","cited_by_count":19},{"id":"2510.15869","title":"Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery","created":"2025-10-17","cited_by_count":17},{"id":"2507.04403","title":"Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion","created":"2025-07-06","cited_by_count":16},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15},{"id":"2509.17336","title":"Mano Technical Report","created":"2025-09-22","cited_by_count":13},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11},{"id":"2507.16524","title":"Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models","created":"2025-07-22","cited_by_count":8},{"id":"2410.18652","title":"$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation","created":"2024-10-24","cited_by_count":6},{"id":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5},{"id":"2509.23804","title":"Controllable Generation of Large-Scale 3D Urban Layouts with Semantic and Structural Guidance","created":"2025-09-28","cited_by_count":1},{"id":"2510.04057","title":"MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation","created":"2025-10-05","cited_by_count":1}],"next_cursor":null}