{"total":32,"rows":[{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2409.18794","title":"Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs","created":"2024-09-27","cited_by_count":62,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2605.18746","title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","created":"2026-05-18","cited_by_count":26,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2505.13948","title":"Memory-Centric Embodied Question Answering","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2507.01634","title":"Depth Anything at Any Condition","created":"2025-07-02","cited_by_count":12,"area":null},{"id":"2412.00091","title":"Graph Canvas for Controllable 3D Scene Generation","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2603.13528","title":"Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis","created":"2026-03-13","cited_by_count":10,"area":null},{"id":"2505.05288","title":"PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes","created":"2025-05-08","cited_by_count":9,"area":null},{"id":"2511.06754","title":"SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation","created":"2025-11-10","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":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2408.04957","title":"LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description","created":"2024-08-09","cited_by_count":7,"area":null},{"id":"2601.12766","title":"Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2505.10604","title":"MIRAGE: A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence","created":"2025-05-15","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2502.07192","title":"OscNet: Machine Learning on CMOS Oscillator Networks","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2510.21160","title":"Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.17411","title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2602.02220","title":"LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.19634","title":"P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2607.21072","title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2506.12610","title":"OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image Classification","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.16690","title":"DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2603.09961","title":"BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.26690","title":"SpatialPoint: Spatial-aware Point Prediction for Embodied Localization","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.12542","title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25334","title":"Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.24886","title":"VLM-based automatic multi-granularity graph representation of building layouts for design informatics","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2610.06235","title":"Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}