V-RoAst applies zero-shot VLMs (Gemini-1.5-flash, GPT-4o-mini) to iRAP road safety attribute classification on a new ThaiRAP image dataset and compares them to CNN baselines, finding better generalization to unseen classes but weaker spatial reasoning.
MapEval: A Map-Based Evaluation of Geo-Spatial Reason- ing in Foundation Models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MapTab introduces a 328-map, 196,800-query benchmark showing that current multimodal LLMs fall far short on multi-criteria route planning from maps-plus-tables.
citing papers explorer
-
V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?
V-RoAst applies zero-shot VLMs (Gemini-1.5-flash, GPT-4o-mini) to iRAP road safety attribute classification on a new ThaiRAP image dataset and compares them to CNN baselines, finding better generalization to unseen classes but weaker spatial reasoning.
-
MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs
MapTab introduces a 328-map, 196,800-query benchmark showing that current multimodal LLMs fall far short on multi-criteria route planning from maps-plus-tables.
- The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes