๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Druv Pai
@druv_pai
Research @thinkymachines, PhD @berkeley_ai | prev @GoogleResearch @GoogleDeepMind | science of scaling deep learning
๊ฐ€์ž… December 2021
521 ํŒ”๋กœ์ž‰ ์ค‘    1.3K ํŒฌ
Why and how do diffusion models memorize vs generalize? Can we have scaling laws for memorization? This is increasingly relevant scientifically and pragmatically (e.g. Sora 2). ๐Ÿšจ Our new preprint "On the Edge of Memorization in Diffusion Models" addresses this timely question!
๋” ๋ณด๊ธฐ