{"total":36,"rows":[{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348,"area":null},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"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":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158,"area":null},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146,"area":null},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118,"area":null},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86,"area":null},{"id":"2204.05186","title":"Correcting Robot Plans with Natural Language Feedback","created":"2022-04-11","cited_by_count":69,"area":null},{"id":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","cited_by_count":52,"area":null},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49,"area":null},{"id":"2212.06250","title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","created":"2022-12-12","cited_by_count":32,"area":null},{"id":"2112.06390","title":"PartGlot: Learning Shape Part Segmentation from Language Reference Games","created":"2021-12-13","cited_by_count":30,"area":null},{"id":"2304.13826","title":"Programmatically Grounded, Compositionally Generalizable Robotic Manipulation","created":"2023-04-26","cited_by_count":26,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2201.07366","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","created":"2022-01-19","cited_by_count":18,"area":null},{"id":"2301.11564","title":"Learning 6-DoF Fine-grained Grasp Detection Based on Part Affordance Grounding","created":"2023-01-27","cited_by_count":17,"area":null},{"id":"2311.03783","title":"Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI","created":"2023-11-07","cited_by_count":17,"area":null},{"id":"2207.11569","title":"Robots Enact Malignant Stereotypes","created":"2022-07-23","cited_by_count":14,"area":null},{"id":"2404.18926","title":"Point Cloud Models Improve Visual Robustness in Robotic Learners","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2403.13289","title":"Text-to-3D Shape Generation","created":"2024-03-20","cited_by_count":13,"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":"2410.10719","title":"4-LEGS: 4D Language Embedded Gaussian Splatting","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2205.09710","title":"Voxel-informed Language Grounding","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2212.05011","title":"LADIS: Language Disentanglement for 3D Shape Editing","created":"2022-12-09","cited_by_count":10,"area":null},{"id":"2305.13668","title":"Grounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2312.06116","title":"Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods","created":"2023-12-11","cited_by_count":6,"area":null},{"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":"2210.00434","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2309.03483","title":"DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2311.06694","title":"Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2407.02846","title":"Multi-Task Domain Adaptation for Language Grounding with 3D Objects","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2302.10282","title":"Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2505.06030","title":"Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2406.17876","title":"ET tu, CLIP? Addressing Common Object Errors for Unseen Environments","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2601.09613","title":"CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.10130","title":"Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":null}