Research map / Probabilistic and scientific modeling / Molecules and proteins
Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis
Check 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 |
|---|---|---|---|
| Add contrastive loss to align image latents with molecular embeddings (ablation) | Mol2Image · Cell Painting, training molecules | Corr: 58.8 -> 63.2 | Helped |
| Add contrastive loss to align image latents with molecular embeddings (ablation) | Mol2Image · Cell Painting, held-out molecules | Corr: 55.7 -> 62.6 | Helped |
| Add contrastive loss (ablation) | Mol2Image · Cell Painting, training molecules | SWD: 3.68 -> 4.63 | Hurt |
| Add contrastive loss (ablation) | Mol2Image · Cell Painting, held-out molecules | SWD: 3.41 -> 4.27 | Hurt |
| Add the Haar pyramid architecture for coarse-to-fine image generation (ablation) | Mol2Image · Cell Painting, training molecules | Corr: 60.0 -> 63.2 | Helped |
| Add the Haar pyramid architecture for coarse-to-fine image generation (ablation) | Mol2Image · Cell Painting, held-out molecules | Corr: 59.1 -> 62.6 | Helped |
| Add contrastive learning to train molecular embeddings (ablation) | Mol2Image molecular embedding · Morphological label prediction | Mean AUC: 0.675 -> 0.810 | Helped |
| Add contrastive learning to train molecular embeddings (ablation) | Mol2Image molecular embedding · Morphological label prediction, held-out molecules | Mean AUC: 0.675 -> 0.683 | Helped |
Closest papers by meaning
- TFG-Flow: Training-free Guidance in Multimodal Generative Flow (ICLR 2025 · similarity 0.85)
- Data-Efficient Molecular Generation with Hierarchical Textual Inversion (ICML 2024 · similarity 0.85)
- CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning (NeurIPS 2025 · similarity 0.85)
- Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning (NeurIPS 2025 · similarity 0.85)
- Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules (NeurIPS 2026 · similarity 0.85)
- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation (ICLR 2025 · similarity 0.84)
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.