Energy-Guided Flow Matching
- Published
- Source
- arXiv
- Paper number
- 844
- Field
- Computer Vision
- arXiv ID
- 2608.05811
Key points
- It replaced flow matching's fixed clean-image endpoint with an endpoint that moves from a low-frequency image to the original, making generation proceed from coarse structure to detail.
- It calculated frequency energy for each image and automatically adjusted heat-diffusion time so that the missing energy is released at the same rate.
- On ImageNet 256×256, it achieved FID 1.55 after 200 training rounds and 1.45 after 600, improving both quality and training efficiency.
- It achieved FID 1.58 at 512×512, and GenEval 0.85 and DPG-Bench 83.9 for text-to-image generation, without architectural changes or additional losses.
- It has not yet been evaluated on video and time-varying signals, joint text-image models, embodied decision making, or the largest recent foundation models.
Paper links
External research summaries. These are not HDATF publications or measured product results.