Lead story
Ask your AI
Top stories
Models & availability
Latest
← Feed
Copy✕ Close copy menu
Pushing the Limit of Efficient Inference-Time Scaling with Terminal Velocity Matching
Luma presented Terminal Velocity Matching (TVM), a method for efficient inference-time scaling, and challenged readers to distinguish between images generated by 4-step TVM and 50x2-step diffusion.
From the source
Pushing the Limit of Efficient Inference-Time Scaling with Terminal Velocity Matching
lumalabs.ai
Visit source ↗lumalabs.ai
- Announced
- 26 Nov 2025
- Detected
- 03 Sep 2026 14:37 UTC (+280d after)
