Research map / Large language models / Language, safety and interpretability
Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fix forget/input gate biases to assign unit timescales (inverse gamma) in LSTM LM (ablation) | 3-layer LSTM LM · WikiText-2 test | perplexity: 70.23 ± 0.24 -> 68.33 ± 0.12 | Helped |
| RBF interpolation instead of delta-sum downsampling of LSTM features (ablation) | multi-timescale encoding model · fMRI voxel timescale estimates | timescale accuracy in auditory cortex | Helped |
| RBF interpolation instead of delta-sum downsampling (ablation) | multi-timescale encoding model · fMRI prediction across cortex | explained variance | No clear effect |
| direct unit timescales instead of context-length manipulation with stateless LSTM | voxel timescale estimation · fMRI, auditory cortex | timescale interpretability | Helped |
Closest papers by meaning
- fMRI predictors based on language models of increasing complexity recover brain left lateralization (NeurIPS 2024 · similarity 0.89)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · similarity 0.88)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.88)
- Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions (NeurIPS 2024 · similarity 0.87)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.87)
- TopoLM: brain-like spatio-functional organization in a topographic language model (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.