Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
Brain- wavlm: Fine-tuning speech representations with brain responses to language
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
TRIBE v2 is a multimodal AI model that predicts human brain activity more accurately than linear encoding models and recovers established neuroscientific findings through in-silico testing.
Instruction-tuned multimodal LLMs show higher brain alignment (~9-20% over baselines) under task-specific instructions during naturalistic video stimuli, with task-conditioned subspaces and weak semantic coupling.
citing papers explorer
-
How Much is Brain Data Worth for Machine Learning?
Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
-
A foundation model of vision, audition, and language for in-silico neuroscience
TRIBE v2 is a multimodal AI model that predicts human brain activity more accurately than linear encoding models and recovers established neuroscientific findings through in-silico testing.
-
Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli
Instruction-tuned multimodal LLMs show higher brain alignment (~9-20% over baselines) under task-specific instructions during naturalistic video stimuli, with task-conditioned subspaces and weak semantic coupling.