Neural networks are powerful predictors, yet their opacity limits their usefulness in science, where the goal is explanation rather than mere prediction. In neuroscience, for example, deep encoding models accurately predict brain activity in response to natural stimuli, but struggle to reveal which stimulus features dr...
Yash Mehta, C. Singh, Wei-Jia Xu et al.· 1 citation
Auditory attention decoding (AAD) is often evaluated on static, simplified speech scenes that poorly match everyday listening. We introduce MOV-AAD, a large-scale dataset for studying auditory attention under moving, naturalistic conversations. MOV-AAD combines 64-channel EEG with synchronized physiological recordings,...
Xiao-Min He, Vishal Choudhari, Tristan J. Spratt et al.· 0 citations
AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects, is introduced, showing current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content.
Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or"probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds...
LiveMathematicianBench is presented, a dynamic multiple-choice benchmark for research-level mathematical reasoning built from recent arXiv papers published after model training cutoffs, and introduces a thirteen-category logical taxonomy of theorem types, enabling fine-grained evaluation across reasoning forms.