Tag
This paper investigates how language model representations predict neural activity during naturalistic language comprehension across MEG, ECoG, and other recordings. The findings demonstrate that language model features serve as useful neural predictors, but caution against overinterpreting predictive success as evidence for shared neural organization.
This paper introduces Augmented Sparse Encoding Models to interpret brain responses to language using sparse features from language models, validated on high-field 7T fMRI data. It recovers known neural tuning properties and discovers a new voxel population tuned to people-related content.
HeLa-Mem is a bio-inspired memory architecture for LLM agents that models memory as a dynamic graph using Hebbian learning dynamics, featuring episodic and semantic memory stores to improve long-term coherence. Experiments on LoCoMo show superior performance across question categories while using fewer context tokens.