Tag
This paper evaluates the practical effectiveness of Markov boundaries for tabular prediction, finding that while theoretically optimal, current causal discovery methods fail to consistently improve predictive performance due to computational limitations and mismatched optimization goals.
Investigates spatial representation in vision-language models, revealing a consistent bias where models conflate vertical image position with distance, and introduces SpatialTunnel synthetic benchmark to expose this shortcut; finds that better disentangled spatial representations improve robustness.