{"list":"other","total":54,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","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":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2012.02924","title":"iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes","created":"2020-12-05","cited_by_count":155},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57},{"id":"2401.06341","title":"AffordanceLLM: Grounding Affordance from Vision Language Models","created":"2024-01-12","cited_by_count":55},{"id":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52},{"id":"2503.18470","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","created":"2025-03-24","cited_by_count":51},{"id":"2503.14756","title":"SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis","created":"2025-03-18","cited_by_count":26},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25},{"id":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21},{"id":"2202.00185","title":"LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data","created":"2022-02-01","cited_by_count":20},{"id":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20},{"id":"2409.18336","title":"DeBaRA: Denoising-Based 3D Room Arrangement Generation","created":"2024-09-26","cited_by_count":20},{"id":"2412.01550","title":"SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model","created":"2024-12-02","cited_by_count":18},{"id":"2411.16310","title":"Functionality understanding and segmentation in 3D scenes","created":"2024-11-25","cited_by_count":17},{"id":"2405.12460","title":"Physics-based Scene Layout Generation from Human Motion","created":"2024-05-21","cited_by_count":10},{"id":"2502.13372","title":"MoVer: Motion Verification for Motion Graphics Animations","created":"2025-02-19","cited_by_count":10},{"id":"2507.00006","title":"MVGBench: Comprehensive Benchmark for Multi-view Generation Models","created":"2025-06-11","cited_by_count":9},{"id":"2509.00531","title":"MobiAgent: A Systematic Framework for Customizable Mobile Agents","created":"2025-08-30","cited_by_count":9},{"id":"2406.18159","title":"Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models","created":"2024-06-26","cited_by_count":5},{"id":"2509.09332","title":"OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning","created":"2025-09-11","cited_by_count":4},{"id":"2603.02662","title":"Behavior-Aware Anthropometric Scene Generation for Human-Usable 3D Layouts","created":"2026-03-03","cited_by_count":1}],"next_cursor":null}