Research map / 3D vision / 3D generation
CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks
Jeffrey Gu, Minkyu Jeon, Ambri Ma, Serena Yeung-Levy, Ellen D. Zhong
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 |
|---|---|---|---|
| add hypernetwork conditioning instead of concatenation (ablation) | CryoHype · Tomotwin-100 | mean FSCAUC: 0.255 -> 0.346 | Improved |
| use ViT encoder instead of convolutional U-Net encoder (ablation) | CryoHype · Tomotwin-100 | mean FSCAUC: 0.208 -> 0.346 | Improved |
| use ViT encoder instead of MLP encoder (ablation) | CryoHype · Tomotwin-100 | mean FSCAUC: 0.234 -> 0.346 | Improved |
| use CryoHype instead of cryoDRGN | CryoHype · Tomotwin-100 | mean FSCAUC: 0.316 -> 0.346 | Improved |
| use CryoHype instead of cryoDRGN for real-space shape | CryoHype · Tomotwin-100 | mean vIoU: 0.63 -> 0.61 | No clear effect |
| use CryoHype instead of cryoDRGN with 10 structures | CryoHype · Sim2Struct-1000 (10 structures) | mean FSCAUC: 0.434 -> 0.464 | Improved |
| use CryoHype instead of cryoDRGN with 500 structures | CryoHype · Sim2Struct-1000 (500 structures) | mean FSCAUC: 0.216 -> 0.305 | Improved |
| use CryoHype instead of cryoDRGN with 1000 structures | CryoHype · Sim2Struct-1000 (1000 structures) | mean FSCAUC: 0.139 -> 0.232 | Improved |
| use CryoHype instead of cryoDRGN with 1000 structures | CryoHype · Sim2Struct-1000 (1000 structures) | mean Chamfer distance (A): 9.0656 -> 3.0179 | Improved |
| use CryoHype instead of cryoDRGN with 1000 structures | CryoHype · Sim2Struct-1000 (1000 structures) | mean vIoU: 0.2647 -> 0.4181 | Improved |
Closest papers by meaning
- cryoSPHERE: Single-Particle HEterogeneous REconstruction from cryo EM (ICLR 2025 · similarity 0.92)
- CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM (NeurIPS 2024 · similarity 0.92)
- Mixture of neural fields for heterogeneous reconstruction in cryo-EM (NeurIPS 2024 · similarity 0.92)
- Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data (NeurIPS 2025 · similarity 0.91)
- Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery (NeurIPS 2025 · similarity 0.91)
- CryoFM: A Flow-based Foundation Model for Cryo-EM Densities (ICLR 2025 · similarity 0.90)
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.
