SIGIR 2024 W1.6 [fp] Capability-aware Prompt Reformulation Learning for Text-to-Image Generation
Why it's on BrighterTube
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceCapability-aware prompt reformulation for text-to-image generation. Adaptive prompt-engineering technique for large vision-language models.
What you'll learn
A 12-minute video from Association for Computing Machinery (ACM): “SIGIR 2024 W1.6 [fp] Capability-aware Prompt Reformulation Learning for Text-to-Image Generation”.
Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.
Part of ACM SIGIR Conference 2024