{"total":18,"rows":[{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16,"area":"lr"},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2603.27437","title":"SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning","created":"2026-03-28","cited_by_count":15,"area":"lr"},{"id":"2409.15451","title":"Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models","created":"2024-09-23","cited_by_count":12,"area":"lr"},{"id":"2504.18684","title":"SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models","created":"2025-04-25","cited_by_count":11,"area":"lr"},{"id":"2505.03035","title":"MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning","created":"2025-05-05","cited_by_count":9,"area":"lr"},{"id":"2503.09968","title":"Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection","created":"2025-03-13","cited_by_count":6,"area":"lr"},{"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":"2307.11865","title":"CARTIER: Cartographic lAnguage Reasoning Targeted at Instruction Execution for Robots","created":"2023-07-21","cited_by_count":1,"area":"lr"},{"id":"2509.20077","title":"Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"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":"2604.01882","title":"A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2606.28760","title":"Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2608.01185","title":"3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"id":"2610.02021","title":"Task-Adaptive Grounded 3D-Programmers Using 2D VLMs","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.11310","title":"FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}