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.
What can 1.8 billion regressions tell us about the pressures shaping high-level visual representation in brains and machines? bioRxiv, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.