{"total":20,"rows":[{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2412.08468","title":"Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation","created":"2024-12-11","cited_by_count":12,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2408.15966","title":"More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2504.19500","title":"Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2411.16773","title":"MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2506.08002","title":"Aligning Text, Images, and 3D Structure Token-by-Token","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2511.05596","title":"AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2511.12977","title":"ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2509.07825","title":"Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2512.16413","title":"BrepLLM: Enabling Large Language Models to Understand Boundary Representations","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2605.28241","title":"PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.29136","title":"On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2610.18604","title":"LLM2R: From Large Language Models to 3D Reassemblers","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}