{"list":"other","total":60,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"2312.14074","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","created":"2023-12-21","cited_by_count":95},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2503.23765","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","created":"2025-03-31","cited_by_count":79},{"id":"2310.14540","title":"Evaluating Spatial Understanding of Large Language Models","created":"2023-10-23","cited_by_count":66},{"id":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2402.12058","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","created":"2024-02-19","cited_by_count":57},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","cited_by_count":51},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44},{"id":"2312.09579","title":"MobileSAMv2: Faster Segment Anything to Everything","created":"2023-12-15","cited_by_count":42},{"id":"2501.07556","title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training","created":"2025-01-13","cited_by_count":41},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38},{"id":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31},{"id":"2410.02479","title":"Cross-Embodiment Dexterous Grasping with Reinforcement Learning","created":"2024-10-03","cited_by_count":27},{"id":"2502.06428","title":"CoS: Chain-of-Shot Prompting for Long Video Understanding","created":"2025-02-10","cited_by_count":27},{"id":"2406.09489","title":"Language-driven Grasp Detection","created":"2024-06-13","cited_by_count":26},{"id":"2410.23968","title":"EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planning","created":"2024-10-31","cited_by_count":24},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23},{"id":"2412.00171","title":"RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World","created":"2024-11-29","cited_by_count":22},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20},{"id":"2311.00530","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","created":"2023-11-01","cited_by_count":14},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14},{"id":"2504.09848","title":"A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science","created":"2025-04-14","cited_by_count":12},{"id":"2501.15953","title":"Understanding Long Videos via LLM-Powered Entity Relation Graphs","created":"2025-01-27","cited_by_count":11},{"id":"2410.11187","title":"Multiview Scene Graph","created":"2024-10-15","cited_by_count":9},{"id":"2311.14100","title":"MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction","created":"2023-11-23","cited_by_count":7}],"next_cursor":null}