Research map / Video / Video segmentation and tracking
Hyper-HMM: aligning human brains and semantic features in a common latent event space
Caroline Lee, Jane Han, Ma Feilong, Guo Jiahui, James Haxby, Christopher Baldassano
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| learned projection matrices Wi instead of random normal projections (ablation) | Hyper-HMM · fMRI angular gyrus, held-out runs, fMRI-fMRI event clustering | variance explained: p < 0.001 | Improved |
| learned projection matrices Wi instead of random normal projections (ablation) | Hyper-HMM · fMRI angular gyrus, held-out runs, fMRI-stimulus match | variance explained: p < 0.001 | Improved |
| learned projection matrices Wi instead of random normal projections (ablation) | Hyper-HMM · fMRI posterior medial cortex, held-out runs, fMRI-stimulus match | variance explained: p = 0.0027 | Improved |
| set latent dimensionality D = 3 rather than D = 2 (ablation) | Hyper-HMM · fMRI held-out clustering (fMRI and stimulus) | variance explained: slightly reduced performance for D = 2 | Improved |
| increase latent dimensionality from D = 3 up to D = 8 (ablation) | Hyper-HMM · fMRI held-out clustering (fMRI and stimulus) | variance explained: substantially reduced performance as D increased to 8 | Hurt |
| vary latent dimensionality D across range (ablation) | Hyper-HMM · fMRI held-out clustering vs random baseline | variance explained | No clear effect |
| increase noise amplitude up to twice the signal amplitude | Hyper-HMM · simulated fMRI, ground-truth boundary recovery | boundary recovery fraction | No clear effect |
| raise noise amplitude to several times the signal | Hyper-HMM · simulated fMRI, held-out latent alignment | variance explained | Hurt |
Closest papers by meaning
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models (NeurIPS 2025 · similarity 0.87)
- Bridging the Semantic Latent Space between Brain and Machine: Similarity Is All You Need (AAAI 2024 · similarity 0.87)
- BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity (ICLR 2024 · similarity 0.86)
- SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments (ICLR 2025 · similarity 0.86)
- Finding Shared Decodable Concepts and their Negations in the Brain (ICLR 2025 · similarity 0.86)
- Improving Semantic Understanding in Speech Language Models via Brain-tuning (ICLR 2025 · similarity 0.86)
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.
