Orientation information is recoverable from MLLM visual encoder embeddings via linear regression, contradicting the hypothesis that failures originate in the encoders.
Spatialviz-bench: An mllm benchmark for spatial visualiza- tion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
MLLMs show a large gap in spatial mathematical reasoning compared to humans, and a new 10,000-problem dataset helps narrow it through training.
citing papers explorer
-
Why MLLMs Struggle to Determine Object Orientations
Orientation information is recoverable from MLLM visual encoder embeddings via linear regression, contradicting the hypothesis that failures originate in the encoders.
-
Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation
MLLMs show a large gap in spatial mathematical reasoning compared to humans, and a new 10,000-problem dataset helps narrow it through training.