{"total":95,"rows":[{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559,"area":null},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165,"area":null},{"id":"2312.00860","title":"Segment Any 3D Gaussians","created":"2023-12-01","cited_by_count":161,"area":null},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135,"area":null},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135,"area":"agents"},{"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":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99,"area":null},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91,"area":null},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89,"area":null},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69,"area":null},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","cited_by_count":69,"area":null},{"id":"2404.03650","title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","created":"2024-04-04","cited_by_count":69,"area":"mllm"},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2304.12308","title":"Segment Anything in 3D with Radiance Fields","created":"2023-04-24","cited_by_count":62,"area":null},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54,"area":null},{"id":"2303.12786","title":"FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models","created":"2023-03-22","cited_by_count":47,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2309.14491","title":"Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving","created":"2023-09-25","cited_by_count":37,"area":"driving"},{"id":"2311.09571","title":"3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation","created":"2023-11-16","cited_by_count":35,"area":null},{"id":"2305.16404","title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","created":"2023-05-25","cited_by_count":34,"area":null},{"id":"2401.12202","title":"OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics","created":"2024-01-22","cited_by_count":34,"area":null},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"area":null},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2411.04999","title":"DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation","created":"2024-11-07","cited_by_count":32,"area":"mllm"},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25,"area":null},{"id":"2305.16133","title":"OVO: Open-Vocabulary Occupancy","created":"2023-05-25","cited_by_count":24,"area":null},{"id":"2304.08587","title":"Grounding Classical Task Planners via Vision-Language Models","created":"2023-04-17","cited_by_count":23,"area":"mllm"},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2410.22489","title":"Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation","created":"2024-10-29","cited_by_count":20,"area":null},{"id":"2412.08331","title":"SLGaussian: Fast Language Gaussian Splatting in Sparse Views","created":"2024-12-11","cited_by_count":18,"area":null},{"id":"2312.04533","title":"Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models","created":"2023-12-07","cited_by_count":16,"area":"mllm"},{"id":"2412.01807","title":"Occam's LGS: An Efficient Approach for Language Gaussian Splatting","created":"2024-12-02","cited_by_count":16,"area":null},{"id":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","cited_by_count":16,"area":"mllm"},{"id":"2309.15065","title":"Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2406.17659","title":"DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning","created":"2024-06-25","cited_by_count":14,"area":"mllm"},{"id":"2401.02402","title":"3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation","created":"2024-01-04","cited_by_count":13,"area":null},{"id":"2404.02157","title":"Segment Any 3D Object with Language","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13,"area":null},{"id":"2408.02454","title":"VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments","created":"2024-08-05","cited_by_count":11,"area":"mllm"},{"id":"2409.20445","title":"Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments","created":"2024-09-30","cited_by_count":9,"area":"mllm"},{"id":"2212.04412","title":"Task Bias in Vision-Language Models","created":"2022-12-08","cited_by_count":8,"area":"mllm"},{"id":"2506.07857","title":"LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2506.16652","title":"CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity","created":"2025-06-19","cited_by_count":8,"area":"diffusion"},{"id":"2303.10962","title":"Neural Implicit Vision-Language Feature Fields","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2309.14338","title":"3D Indoor Instance Segmentation in an Open-World","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2508.20063","title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations","created":"2025-08-27","cited_by_count":7,"area":null},{"id":"2411.15714","title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond","created":"2024-11-24","cited_by_count":6,"area":"mllm"},{"id":"2507.06719","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","created":"2025-07-09","cited_by_count":6,"area":"lr"},{"id":"2511.05894","title":"Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning","created":"2025-11-08","cited_by_count":6,"area":"lr"},{"id":"2404.13044","title":"Unified Scene Representation and Reconstruction for 3D Large Language Models","created":"2024-04-19","cited_by_count":5,"area":null},{"id":"2411.13243","title":"XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation","created":"2024-11-20","cited_by_count":5,"area":"lr"},{"id":"2412.13897","title":"Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2501.13338","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2504.06908","title":"UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2505.04813","title":"WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2509.24385","title":"Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2603.26541","title":"OVI-MAP:Open-Vocabulary Instance-Semantic Mapping","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2405.20795","title":"InsightSee: Advancing Multi-agent Vision-Language Models for Enhanced Visual Understanding","created":"2024-05-31","cited_by_count":3,"area":"mllm"},{"id":"2408.08591","title":"Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation","created":"2024-08-16","cited_by_count":3,"area":null},{"id":"2504.11754","title":"GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision","created":"2025-04-16","cited_by_count":3,"area":null},{"id":"2506.11585","title":"OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2410.07394","title":"Structured Spatial Reasoning with Open Vocabulary Object Detectors","created":"2024-10-09","cited_by_count":2,"area":"lr"},{"id":"2503.10331","title":"OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2508.09470","title":"CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2601.07695","title":"Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model","created":"2026-01-12","cited_by_count":2,"area":"lr"},{"id":"2409.05413","title":"From Words to Poses: Enhancing Novel Object Pose Estimation with Vision Language Models","created":"2024-09-09","cited_by_count":1,"area":"mllm"},{"id":"2410.04529","title":"In-Place Panoptic Radiance Field Segmentation with Perceptual Prior for 3D Scene Understanding","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2502.08903","title":"3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning","created":"2025-02-13","cited_by_count":1,"area":"lr"},{"id":"2502.12481","title":"Predicate Hierarchies Improve Few-Shot State Classification","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2604.26262","title":"Semantic Foam: Unifying Spatial and Semantic Scene Decomposition","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.13152","title":"EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.21292","title":"Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2310.04981","title":"Compositional Semantics for Open Vocabulary Spatio-semantic Representations","created":"2023-10-08","cited_by_count":0,"area":"mllm"},{"id":"2311.04783","title":"VioLA: Aligning Videos to 2D LiDAR Scans","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2501.03304","title":"LiLMaps: Learnable Implicit Language Maps","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2511.00785","title":"Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2604.17155","title":"Instant Colorization of Gaussian Splats","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.27178","title":"FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2609.28222","title":"From Alignment to Fusion in 3D Vision-Language","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.02021","title":"Task-Adaptive Grounded 3D-Programmers Using 2D VLMs","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}