{"total":64,"rows":[{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60,"area":"lr"},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44,"area":"lr"},{"id":"2411.05755","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","created":"2024-11-08","cited_by_count":37,"area":"lr"},{"id":"2506.09839","title":"OctoNav: Towards Generalist Embodied Navigation","created":"2025-06-11","cited_by_count":34,"area":"lr"},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31,"area":"lr"},{"id":"2502.14254","title":"Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation","created":"2025-02-20","cited_by_count":30,"area":"lr"},{"id":"2507.13019","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","created":"2025-07-17","cited_by_count":25,"area":"lr"},{"id":"2411.16425","title":"TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation","created":"2024-11-25","cited_by_count":15,"area":"lr"},{"id":"2505.20640","title":"IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2505.22050","title":"Reinforced Reasoning for Embodied Planning","created":"2025-05-28","cited_by_count":12,"area":"lr"},{"id":"2605.22816","title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2410.03907","title":"ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities","created":"2024-10-04","cited_by_count":9,"area":"lr"},{"id":"2505.03035","title":"MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning","created":"2025-05-05","cited_by_count":9,"area":"lr"},{"id":"2512.05955","title":"SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models","created":"2025-12-05","cited_by_count":8,"area":"lr"},{"id":"2503.10042","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability","created":"2025-03-13","cited_by_count":6,"area":"lr"},{"id":"2604.22409","title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","created":"2026-04-24","cited_by_count":6,"area":"lr"},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2511.17384","title":"IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4,"area":"lr"},{"id":"2502.00931","title":"VL-Nav: Neuro-Symbolic Reasoning-based Vision-Language Navigation","created":"2025-02-02","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2512.15160","title":"EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2605.12620","title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.14504","title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2607.06165","title":"EAGOR: Embodied Reasoning in Omni-direction","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2506.16805","title":"Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes","created":"2025-06-20","cited_by_count":2,"area":"lr"},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2605.22036","title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2410.21842","title":"Diffusion as Reasoning: Enhancing Object Navigation via Diffusion Model Conditioned on LLM-based Object-Room Knowledge","created":"2024-10-29","cited_by_count":1,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2512.03284","title":"SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding","created":"2025-12-02","cited_by_count":1,"area":"lr"},{"id":"2601.11729","title":"SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models","created":"2026-01-16","cited_by_count":1,"area":"lr"},{"id":"2602.19063","title":"Direction-aware 3D Large Multimodal Models","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2603.07181","title":"FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigation","created":"2026-03-07","cited_by_count":1,"area":"lr"},{"id":"2603.13091","title":"Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2603.16947","title":"LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2603.21577","title":"Mind over Space: Can Multimodal Large Language Models Mentally Navigate?","created":"2026-03-23","cited_by_count":1,"area":"lr"},{"id":"2606.01565","title":"Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.17599","title":"ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2512.15776","title":"Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying","created":"2025-12-13","cited_by_count":0,"area":"lr"},{"id":"2601.07553","title":"VirtualEnv: A Platform for Embodied AI Research","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2602.00611","title":"Structured Self-Consistency:A Multi-Task Evaluation of LLMs on VirtualHome","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2602.20055","title":"CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation","created":"2026-02-23","cited_by_count":0,"area":"lr"},{"id":"2603.05642","title":"Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2603.29165","title":"LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning","created":"2026-03-31","cited_by_count":0,"area":"lr"},{"id":"2605.11534","title":"PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.23165","title":"Autonomous Frontier-Based Exploration with VLM Guidance","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2605.31404","title":"The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2607.10744","title":"Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation","created":"2026-07-12","cited_by_count":0,"area":"lr"},{"id":"2608.28270","title":"Spatial-Semantic Reasoning using Large Language Models for Efficient UAV Search Operations","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.37187","title":"InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.40325","title":"WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.14541","title":"GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.14679","title":"HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.17131","title":"SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}