FungiTastic Baseline

Training-free fine-grained semantic segmentation in low-data regimes.

NewtPhys

A physics-grounded benchmark for evaluating foundation models on Newtonian reasoning.

CAD-Assistant

Tool-augmented VLLMs as generic CAD task solvers.

All Languages Matter

Evaluating LMMs on culturally diverse visual reasoning across 100 languages.

Does Complexity Pay Off?

Applying advanced algorithms to depression detection on the GLOBEM dataset.