{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2306.03908","title":"SAM3D: Segment Anything in 3D Scenes","created":"2023-06-06","cited_by_count":157},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51},{"id":"2406.17741","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds","created":"2024-06-25","cited_by_count":50},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41},{"id":"2303.06880","title":"Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection","created":"2023-03-13","cited_by_count":39},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34},{"id":"2502.20041","title":"3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds","created":"2025-02-27","cited_by_count":30},{"id":"2411.19626","title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding","created":"2024-11-29","cited_by_count":28},{"id":"2503.07360","title":"AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance","created":"2025-03-10","cited_by_count":27},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26},{"id":"2510.20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding","created":"2025-10-23","cited_by_count":26},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"2503.11423","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","created":"2025-03-14","cited_by_count":24},{"id":"2309.07510","title":"Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions","created":"2023-09-14","cited_by_count":23},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23},{"id":"2408.13024","title":"Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding","created":"2024-08-23","cited_by_count":22},{"id":"2504.04744","title":"Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions","created":"2025-04-07","cited_by_count":19},{"id":"2309.09556","title":"Affordance-Driven Next-Best-View Planning for Robotic Grasping","created":"2023-09-18","cited_by_count":16},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11},{"id":"2510.05057","title":"StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation","created":"2025-10-06","cited_by_count":11},{"id":"2403.08355","title":"NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation","created":"2024-03-13","cited_by_count":10},{"id":"2004.08644","title":"A Deep Learning Approach to Object Affordance Segmentation","created":"2020-04-18","cited_by_count":9},{"id":"2503.09243","title":"GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation","created":"2025-03-12","cited_by_count":9},{"id":"2503.09320","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","created":"2025-03-12","cited_by_count":9},{"id":"2504.11218","title":"3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians","created":"2025-04-15","cited_by_count":9},{"id":"2505.24103","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","created":"2025-05-30","cited_by_count":9},{"id":"2508.08240","title":"ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks","created":"2025-08-11","cited_by_count":9},{"id":"2210.08537","title":"Learning 6-DoF Task-oriented Grasp Detection via Implicit Estimation and Visual Affordance","created":"2022-10-16","cited_by_count":8},{"id":"2504.15650","title":"AffordanceSAM: Segment Anything Once More in Affordance Grounding","created":"2025-04-22","cited_by_count":6},{"id":"2506.12009","title":"Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale","created":"2025-06-13","cited_by_count":6},{"id":"2508.01651","title":"Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning","created":"2025-08-03","cited_by_count":6},{"id":"2508.07877","title":"Selective Contrastive Learning for Weakly Supervised Affordance Grounding","created":"2025-08-11","cited_by_count":6},{"id":"2508.08896","title":"Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors","created":"2025-08-12","cited_by_count":4},{"id":"2510.17384","title":"Closed-Loop Transfer for Weakly-supervised Affordance Grounding","created":"2025-10-20","cited_by_count":4},{"id":"2507.23772","title":"SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting","created":"2025-07-31","cited_by_count":3},{"id":"2509.06233","title":"O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation","created":"2025-09-07","cited_by_count":3},{"id":"2410.11363","title":"Visual-Geometric Collaborative Guidance for Affordance Learning","created":"2024-10-15","cited_by_count":2}],"next_cursor":null}