Research map / Image generation / Fast diffusion sampling
Planning with Diffusion for Flexible Behavior Synthesis
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 |
|---|---|---|---|
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Maze2D U-Maze · Maze2D U-Maze | score: 47.4 -> 113.9 | Helped |
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Maze2D Medium · Maze2D Medium | score: 34.9 -> 121.5 | Helped |
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Maze2D Large · Maze2D Large | score: 58.6 -> 123.0 | Helped |
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Multi2D U-Maze · Multi2D U-Maze | score: 41.2 -> 128.9 | Helped |
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Multi2D Medium · Multi2D Medium | score: 15.4 -> 127.2 | Helped |
| Use trajectory diffusion with goal inpainting instead of the strongest listed baseline | Multi2D Large · Multi2D Large | score: 13.9 -> 132.1 | Helped |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · HalfCheetah Medium-Expert | score: 105.9 -> 88.9 | Hurt |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · Hopper Medium-Expert | score: 110.0 -> 103.3 | Hurt |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · Walker2d Medium-Expert | score: 109.6 -> 106.9 | Hurt |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · HalfCheetah Medium | score: 47.4 -> 42.8 | Hurt |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · Hopper Medium | score: 95.4 -> 74.3 | Hurt |
| Use Diffuser instead of the strongest listed baseline | D4RL locomotion · Walker2d Medium | score: 79.0 -> 79.6 | Helped |
Closest papers by meaning
- Prior-Guided Diffusion Planning for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.92)
- Model-based Diffusion for Trajectory Optimization (NeurIPS 2024 · similarity 0.91)
- Score Regularized Policy Optimization through Diffusion Behavior (ICLR 2024 · similarity 0.91)
- Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving (CVPR 2024 · similarity 0.90)
- DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising (NeurIPS 2026 · similarity 0.90)
- State-Covering Trajectory Stitching for Diffusion Planners (NeurIPS 2025 · similarity 0.89)
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.