Research map / Image generation / Fast diffusion sampling
One Algorithm to Align Them All
Boyi Pang, Savva Ignatyev, Vladimir Ippolitov, Ramil Khafizov, Yurii Melnik, Oleg Voynov, Maksim Nakhodnov, Aibek Alanov, Xiaopeng Fan, Peter Wonka, Evgeny Burnaev
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 |
|---|---|---|---|
| joint transport of a segment with intermediate interpolated points instead of two endpoints only (ablation) | joint rectified-flow inference (video, WAN 2.1) · video structural alignment | depth MAE | Improved |
| use the model velocity at the segment midpoint as anchor velocity instead of the mean of endpoint velocities (ablation) | joint rectified-flow inference · video and image structural alignment | depth MAE / DIFT distance | Improved |
| smooth weight schedule for anchor co-guidance instead of a hard cutoff (ablation) | joint rectified-flow inference (FLUX.1-dev images) · image alignment ablation | DIFT distance | Improved |
| joint segment transport vs MatchDiffusion joint generation | WAN 2.1 video · video alignment | depth alignment | Improved |
| joint transport vs RF-Inversion editing | FLUX.1-dev · image pairs | structural alignment (DIFT, depth) | Improved |
| use the method with Trellis.1 (text-conditioned) backbone | Trellis.1 · text-to-3D | DIFT structural alignment | Mixed |
| inference-based joint transport instead of SDS-based A3D | 3D generation · text-to-3D | generation time | Improved |
Closest papers by meaning
- Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation (NeurIPS 2025 · similarity 0.87)
- Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference (NeurIPS 2026 · similarity 0.86)
- SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation (NeurIPS 2026 · similarity 0.86)
- Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion (CVPR 2025 · similarity 0.86)
- Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior (CVPR 2024 · similarity 0.86)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.85)
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.
