Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
- 12 September 2026
- book chapter
- Published by Springer Nature
- p. 22-39
Abstract
No abstract availableKeywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models2025
- NVILA: Efficient Frontier Visual Language Models2025
- RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics2025
- DepthCues: Evaluating Monocular Depth Perception in Large Vision Models2025
- Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models2025
- BLINK: Multimodal Large Language Models Can See but Not Perceive2024
- Improved Baselines with Visual Instruction Tuning2024
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities2024
- LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models2023
- ProgPrompt: Generating Situated Robot Task Plans using Large Language Models2023