{"total":195,"rows":[{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"area":null},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2407.07775","title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs","created":"2024-07-10","cited_by_count":73,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"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":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"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":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25,"area":null},{"id":"2505.22657","title":"3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model","created":"2025-05-28","cited_by_count":25,"area":null},{"id":"2510.11712","title":"DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training","created":"2025-10-13","cited_by_count":24,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"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,"area":null},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"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":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2412.04247","title":"3D Part Segmentation via Geometric Aggregation of 2D Visual Features","created":"2024-12-05","cited_by_count":15,"area":null},{"id":"2503.10745","title":"Unifying 2D and 3D Vision-Language Understanding","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2503.14503","title":"The Power of Context: How Multimodality Improves Image Super-Resolution","created":"2025-03-18","cited_by_count":15,"area":null},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2410.14682","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2412.06322","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","created":"2024-12-09","cited_by_count":13,"area":null},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2505.20981","title":"RefAV: Towards Planning-Centric Scenario Mining","created":"2025-05-27","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":"2508.01608","title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","created":"2025-08-03","cited_by_count":12,"area":null},{"id":"2511.15700","title":"First Frame Is the Place to Go for Video Content Customization","created":"2025-11-19","cited_by_count":12,"area":null},{"id":"2502.04531","title":"AnyPlace: Learning Generalized Object Placement for Robot Manipulation","created":"2025-02-06","cited_by_count":11,"area":null},{"id":"2603.12255","title":"Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2508.15874","title":"Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2509.08757","title":"SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation","created":"2025-09-10","cited_by_count":10,"area":null},{"id":"2509.23563","title":"RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation","created":"2025-09-28","cited_by_count":10,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","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":"2505.24870","title":"GenSpace: Benchmarking Spatially-Aware Image Generation","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2407.05047","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","created":"2024-07-06","cited_by_count":8,"area":null},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2505.12703","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2505.22566","title":"Universal Visuo-Tactile Video Understanding for Embodied Interaction","created":"2025-05-28","cited_by_count":8,"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":"2509.11514","title":"LVLMs are Bad at Overhearing Human Referential Communication","created":"2025-09-15","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":"2504.13351","title":"Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7,"area":null},{"id":"2512.17875","title":"Visually Prompted Benchmarks Are Surprisingly Fragile","created":"2025-12-19","cited_by_count":7,"area":null},{"id":"2605.08747","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","created":"2026-05-09","cited_by_count":7,"area":null},{"id":"2502.07183","title":"Space-Aware Instruction Tuning: Dataset and Benchmark for Guide Dog Robots Assisting the Visually Impaired","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2510.15148","title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2511.11702","title":"Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement","created":"2025-11-12","cited_by_count":6,"area":null},{"id":"2604.07296","title":"OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2607.10383","title":"ABot-N1: Toward a General Visual Language Navigation Foundation Model","created":"2026-07-11","cited_by_count":6,"area":null},{"id":"2607.12477","title":"Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence","created":"2026-07-14","cited_by_count":6,"area":null},{"id":"2502.08643","title":"A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2507.15130","title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2605.13169","title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","created":"2026-05-13","cited_by_count":5,"area":null},{"id":"2605.22819","title":"Cambrian-P: Pose-Grounded Video Understanding","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2407.03969","title":"Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2409.10683","title":"MotIF: Motion Instruction Fine-tuning","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2410.05869","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2509.16567","title":"V-CECE: Visual Counterfactual Explanations via Conceptual Edits","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2404.06413","title":"Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2509.18626","title":"The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2603.00461","title":"ReMoT: Reinforcement Learning with Motion Contrast Triplets","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2604.02020","title":"Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.03175","title":"Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2410.07658","title":"SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2505.10875","title":"A Light and Smart Wearable Platform with Multimodal Foundation Model for Enhanced Spatial Reasoning in People with Blindness and Low Vision","created":"2025-05-16","cited_by_count":2,"area":null}],"next_cursor":"100"}