Research map / Image generation / Fast diffusion sampling
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
Sai Niranjan Ramachandran, Suvrit Sra
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 |
|---|---|---|---|
| condition flow matching on decision-tree hierarchical priors (TreeFlow) instead of TabDDPM | tabular diffusion generation · tabular benchmarks | runtime: 2X faster than TabDDPM | Improved |
| use TreeFlow instead of sdv baselines and TabDDPM | tabular generation · 5 tabular benchmarks | Wasserstein distance: lowest on 4/5 benchmarks | Improved |
| use TreeFlow instead of baselines | tabular generation · 5 tabular benchmarks | TSTR accuracy: highest on 3/5 benchmarks (98.1 on Wine, 93.9 on Cancer) | Mixed |
| distill the full tree decision path into a neural network (DSM-Tree) versus the teacher tree | decision tree classifier · 5 tabular datasets | accuracy: within 2% on 4/5 datasets, +3.7% on Heart Disease | Mixed |
Closest papers by meaning
- Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree (ICML 2024 · similarity 0.88)
- Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion (ICML 2025 · similarity 0.86)
- TREE-G: Decision Trees Contesting Graph Neural Networks (AAAI 2024 · similarity 0.85)
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization (ICLR 2024 · similarity 0.85)
- Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models (NeurIPS 2026 · similarity 0.85)
- Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization (ICLR 2024 · 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.
