{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47},{"id":"2202.01993","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","created":"2022-02-04","cited_by_count":47},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40},{"id":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33},{"id":"2103.05368","title":"ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments","created":"2021-03-09","cited_by_count":28},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27},{"id":"2403.15604","title":"Investigating Use Cases of AI-Powered Scene Description Applications for Blind and Low Vision People","created":"2024-03-22","cited_by_count":24},{"id":"2402.01735","title":"VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models","created":"2024-01-29","cited_by_count":23},{"id":"2308.10417","title":"The Change You Want to See (Now in 3D)","created":"2023-08-21","cited_by_count":17},{"id":"2208.09870","title":"Objects Can Move: 3D Change Detection by Geometric Transformation Constistency","created":"2022-08-21","cited_by_count":13},{"id":"2408.06926","title":"SceneGPT: A Language Model for 3D Scene Understanding","created":"2024-08-13","cited_by_count":12},{"id":"2408.12093","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","created":"2024-08-22","cited_by_count":12},{"id":"2412.03911","title":"Multi-View Pose-Agnostic Change Localization with Zero Labels","created":"2024-12-05","cited_by_count":12},{"id":"2111.14422","title":"Agent-Centric Relation Graph for Object Visual Navigation","created":"2021-11-29","cited_by_count":10},{"id":"2309.12172","title":"SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset","created":"2023-09-21","cited_by_count":10},{"id":"2411.19162","title":"Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs","created":"2024-11-28","cited_by_count":10},{"id":"2503.12844","title":"GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance","created":"2025-03-17","cited_by_count":10},{"id":"2505.19325","title":"What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study","created":"2025-05-25","cited_by_count":6},{"id":"2303.05676","title":"Rearrange Indoor Scenes for Human-Robot Co-Activity","created":"2023-03-10","cited_by_count":5},{"id":"2310.09276","title":"Transformer-based Multimodal Change Detection with Multitask Consistency Constraints","created":"2023-10-13","cited_by_count":4},{"id":"2504.07867","title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos","created":"2025-04-10","cited_by_count":4}],"next_cursor":null}