Research map / Image generation / Fast diffusion sampling
End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
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 |
|---|---|---|---|
| Train the VLD components end-to-end instead of pretraining the VAE and then training diffusion | VLD · Semi-leptonic t̄t test set | Wasserstein distance: 402.32 -> 108.76 | Helped |
| Use a latent representation and diffuse in latent space rather than denoising partons directly | VLD · Semi-leptonic t̄t test set | Wasserstein distance: 2478.35 -> 108.76 | Helped |
| Add a conditional encoder with an unconditional decoder (ablation) | VLD · Semi-leptonic t̄t test set | Wasserstein distance: 108.76 -> 73.56 | Helped |
| Add a conditional encoder and conditional decoder (ablation) | VLD · Semi-leptonic t̄t test set | Wasserstein distance: 108.76 -> 389.62 | Hurt |
| Use a conditional encoder with an unconditional decoder (ablation) | VLD · Semi-leptonic t̄t test set | KL divergence (64 bins): 3.47 -> 5.77 | Hurt |
| Use a conditional encoder and conditional decoder (ablation) | VLD · Semi-leptonic t̄t test set | Energy distance: 7.59 -> 25.39 | Hurt |
Closest papers by meaning
- Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation (NeurIPS 2025 · similarity 0.85)
- Improved sampling via learned diffusions (ICLR 2024 · similarity 0.84)
- Text2PDE: Latent Diffusion Models for Accessible Physics Simulation (ICLR 2025 · similarity 0.84)
- Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models (CVPR 2025 · similarity 0.84)
- Physics-Informed Diffusion Models (ICLR 2025 · similarity 0.83)
- Stitched Value Model for Diffusion Alignment (NeurIPS 2026 · similarity 0.83)
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.