{"total":65,"rows":[{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29,"area":"lr"},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21,"area":null},{"id":"2512.12799","title":"DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning","created":"2025-12-14","cited_by_count":15,"area":"mllm"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2512.13660","title":"Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"area":null},{"id":"2509.17627","title":"OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models","created":"2025-09-22","cited_by_count":9,"area":"diffusion"},{"id":"2601.06806","title":"SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation","created":"2026-01-11","cited_by_count":9,"area":null},{"id":"2603.01142","title":"ArtLLM: Generating Articulated Assets via 3D LLM","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2603.05591","title":"Thinking with Spatial Code for Physical-World Video Reasoning","created":"2026-03-05","cited_by_count":7,"area":"lr"},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6,"area":null},{"id":"2509.24421","title":"Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2604.11792","title":"LottieGPT: Tokenizing Vector Animation for Autoregressive Generation","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2506.20134","title":"From 2D to 3D Cognition: A Brief Survey of General World Models","created":"2025-06-25","cited_by_count":4,"area":"wm"},{"id":"2509.23541","title":"OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2511.20253","title":"Zoo3D: Zero-Shot 3D Object Detection at Scene Level","created":"2025-11-25","cited_by_count":4,"area":null},{"id":"2512.08625","title":"OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2607.13681","title":"Towards Spatial Supersensing in the Wild","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2603.25411","title":"HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2604.16299","title":"Repurposing 3D Generative Model for Autoregressive Layout Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2512.00076","title":"Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2601.16538","title":"OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding","created":"2026-01-23","cited_by_count":2,"area":"lr"},{"id":"2602.22716","title":"SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2604.07997","title":"Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2604.27555","title":"SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2605.20837","title":"ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2606.29395","title":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","created":"2026-06-28","cited_by_count":2,"area":"agents"},{"id":"2607.13586","title":"UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2509.21388","title":"TUN3D: Towards Real-World Scene Understanding from Unposed Images","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2512.05597","title":"Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2604.00528","title":"Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2605.09449","title":"SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2605.15708","title":"3D Segmentation Using Viewpoint-Dependent Spatial Relationships","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2606.05833","title":"Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2607.13454","title":"GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2608.12179","title":"Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.25832","title":"PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2609.38177","title":"Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering","created":"2026-09-29","cited_by_count":1,"area":"mllm"},{"id":"2507.21589","title":"Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2511.07813","title":"Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views","created":"2025-11-11","cited_by_count":0,"area":"lr"},{"id":"2511.11232","title":"DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts","created":"2025-11-14","cited_by_count":0,"area":"moe"},{"id":"2511.18814","title":"DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.10370","title":"GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2603.29798","title":"SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes","created":"2026-03-31","cited_by_count":0,"area":"agents"},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.16832","title":"Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.10701","title":"Vector Map as Language: Toward Unified Remote Sensing Vector Mapping","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.12849","title":"SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.19828","title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31148","title":"PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02908","title":"Holo-Captioning: Toward the Text Equivalent of 3D Scenes","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.03323","title":"PolyLayout: Multi-room Manhattan Layout Estimation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07144","title":"InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.11699","title":"STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2609.12747","title":"Assisted Spatial Cognition Through Vision-Language Models","created":"2026-09-11","cited_by_count":0,"area":"mllm"},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","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"},{"id":"2610.06960","title":"DistScene: Object-to-Scene Distillation for 3D Scene Generation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.18342","title":"CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}