{"total":167,"rows":[{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770,"area":null},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268,"area":"wm"},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229,"area":null},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228,"area":null},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175,"area":null},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"area":null},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139,"area":"lr"},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125,"area":null},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99,"area":null},{"id":"2312.06644","title":"AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes","created":"2023-12-11","cited_by_count":82,"area":"wm"},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2409.14296","title":"HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation","created":"2024-09-22","cited_by_count":71,"area":null},{"id":"2412.09082","title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method","created":"2024-12-12","cited_by_count":67,"area":null},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2503.15265","title":"DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning","created":"2025-03-19","cited_by_count":65,"area":"alignment"},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2501.10074","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","created":"2025-01-17","cited_by_count":62,"area":"lr"},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58,"area":"deeprl"},{"id":"2401.02695","title":"VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model","created":"2024-01-05","cited_by_count":57,"area":null},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57,"area":"mllm"},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54,"area":null},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2505.08712","title":"NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance","created":"2025-05-13","cited_by_count":49,"area":"diffusion"},{"id":"2602.09153","title":"SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes","created":"2026-02-09","cited_by_count":46,"area":"agents"},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"id":"2410.09874","title":"ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","created":"2024-10-13","cited_by_count":38,"area":"mllm"},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36,"area":"mllm"},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31,"area":null},{"id":"2502.14254","title":"Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation","created":"2025-02-20","cited_by_count":30,"area":"lr"},{"id":"2410.22662","title":"EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2409.18896","title":"S2O: Static to Openable Enhancement for Articulated 3D Objects","created":"2024-09-27","cited_by_count":22,"area":null},{"id":"2505.20460","title":"DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2509.25079","title":"UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation","created":"2025-09-29","cited_by_count":20,"area":"diffusion"},{"id":"2407.18550","title":"ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments","created":"2024-07-26","cited_by_count":16,"area":null},{"id":"2412.05552","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","created":"2024-12-07","cited_by_count":16,"area":"moe"},{"id":"2510.21682","title":"WorldGrow: Generating Infinite 3D World","created":"2025-10-24","cited_by_count":16,"area":null},{"id":"2403.14937","title":"Survey on Modeling of Human-made Articulated Objects","created":"2024-03-22","cited_by_count":14,"area":null},{"id":"2502.14247","title":"Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation","created":"2025-02-20","cited_by_count":14,"area":null},{"id":"2410.14682","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2408.12093","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","created":"2024-08-22","cited_by_count":12,"area":null},{"id":"2503.11081","title":"MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2504.03597","title":"Real-is-Sim: Bridging the Sim-to-Real Gap with a Dynamic Digital Twin","created":"2025-04-04","cited_by_count":12,"area":null},{"id":"2506.15635","title":"FindingDory: A Benchmark to Evaluate Memory in Embodied Agents","created":"2025-06-18","cited_by_count":12,"area":"mllm"},{"id":"2509.17430","title":"EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device","created":"2025-09-22","cited_by_count":12,"area":null},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12,"area":null},{"id":"2405.05852","title":"Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control","created":"2024-05-09","cited_by_count":11,"area":"diffusion"},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2505.20294","title":"GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2506.09665","title":"VideoMat: Extracting PBR Materials from Video Diffusion Models","created":"2025-06-11","cited_by_count":10,"area":"diffusion"},{"id":"2508.13911","title":"PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2512.10949","title":"Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2401.07770","title":"Seeing the Unseen: Visual Common Sense for Semantic Placement","created":"2024-01-15","cited_by_count":9,"area":null},{"id":"2407.06939","title":"Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge","created":"2024-07-09","cited_by_count":9,"area":null},{"id":"2412.01398","title":"Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2510.19732","title":"Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning","created":"2025-10-22","cited_by_count":9,"area":"deeprl"},{"id":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","created":"2025-10-23","cited_by_count":8,"area":null},{"id":"2407.14783","title":"VisFly: An Efficient and Versatile Simulator for Training Vision-based Flight","created":"2024-07-20","cited_by_count":7,"area":"deeprl"},{"id":"2410.02751","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","created":"2024-10-03","cited_by_count":7,"area":"deeprl"},{"id":"2502.07278","title":"Articulate That Object Part (ATOP): 3D Part Articulation via Text and Motion Personalization","created":"2025-02-11","cited_by_count":7,"area":"diffusion"},{"id":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2604.27106","title":"Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations","created":"2026-04-29","cited_by_count":7,"area":null},{"id":"2505.17966","title":"Is Single-View Mesh Reconstruction Ready for Robotics?","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2602.09432","title":"SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2602.12351","title":"LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2604.03696","title":"FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning","created":"2026-04-04","cited_by_count":5,"area":"lr"},{"id":"2402.19007","title":"DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2507.19232","title":"Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene","created":"2025-07-25","cited_by_count":4,"area":null},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2511.08935","title":"Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation","created":"2025-11-12","cited_by_count":4,"area":null},{"id":"2511.17501","title":"Native 3D Editing with Full Attention","created":"2025-11-21","cited_by_count":4,"area":null},{"id":"2511.18801","title":"PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2603.18782","title":"Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2605.24403","title":"Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects","created":"2026-05-23","cited_by_count":4,"area":null},{"id":"2509.04406","title":"Few-step Flow for 3D Generation via Marginal-Data Transport Distillation","created":"2025-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2510.12095","title":"IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2603.04349","title":"FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.16566","title":"VideoMatGen: PBR Materials through Joint Generative Modeling","created":"2026-03-17","cited_by_count":3,"area":"diffusion"},{"id":"2604.16299","title":"Repurposing 3D Generative Model for Autoregressive Layout Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2606.24138","title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","created":"2026-06-23","cited_by_count":3,"area":null},{"id":"2607.20660","title":"Axolotl3D: a Unified Framework for Faithful 3D Shape Completion","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2506.23150","title":"AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation","created":"2025-06-29","cited_by_count":2,"area":null},{"id":"2507.02064","title":"REMI: Reconstructing Episodic Memory During Internally Driven Path Planning","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2511.10040","title":"LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2601.07218","title":"SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.02220","title":"LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation","created":"2026-02-02","cited_by_count":2,"area":null}],"next_cursor":"100"}