{"total":18,"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":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55,"area":"lr"},{"id":"2403.13438","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","created":"2024-03-18","cited_by_count":54,"area":"lr"},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"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":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33,"area":"lr"},{"id":"2510.17439","title":"From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors","created":"2025-10-20","cited_by_count":28,"area":"lr"},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2512.09619","title":"GLaD: Geometric Latent Distillation for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":11,"area":"lr"},{"id":"2508.13968","title":"RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation","created":"2025-08-19","cited_by_count":4,"area":"lr"},{"id":"2509.24385","title":"Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2602.07082","title":"MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2606.02742","title":"Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.11173","title":"When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoning","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2610.05026","title":"GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.11310","title":"FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}