๋ณธ๋ฌธ์œผ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ
buildradar
Sign in

FoundationVision/VAR

@FoundationVision

[NeurIPS 2024 Best Paper Award][GPT beats diffusion๐Ÿ”ฅ] [scaling laws in visual generation๐Ÿ“ˆ] 'Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction' ๊ณต์‹ ๊ตฌํ˜„์ฒด. ์ž๊ฐ€ ํšŒ๊ท€ ์ด๋ฏธ์ง€ ์ƒ์„ฑ์„ ์œ„ํ•œ *์ดˆ๊ฐ„๋‹จํ•˜๊ณ  ์‚ฌ์šฉ์ž ์นœํ™”์ ์ด๋ฉด์„œ๋„ ์ตœ์ฒจ๋‹จ์ธ* ์ฝ”๋“œ๋ฒ ์ด์Šค!

โ†— GitHub์—์„œ ์—ด๊ธฐ
์Šคํƒ€
8,728
ํฌํฌ
572
์–ธ์–ด
Jupyter Notebook
๋ผ์ด์„ ์Šค
MIT
๋งˆ์ง€๋ง‰ ํ‘ธ์‹œ
10๊ฐœ์›” ์ „
Jupyter Notebookdiffusion-modelsgenerative-aigptlarge-language-modelsimage-generationtransformersgenerative-modelautoregressive-modelsgpt-2vision-transformerneuripsauto-regressive-model

๊ด€๋ จ ์ธํ…” (0)

์•„์ง ๊ด€๋ จ ์ธํ…”์ด ์—†์Šต๋‹ˆ๋‹ค

์ด ์ €์žฅ์†Œ๋Š” radar๊ฐ€ ์ถ”์ ํ•˜๋Š” ์–ด๋–ค ์†Œ์Šค์—๋„ ์•„์ง ๋“ฑ์žฅํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค. ์ˆ˜์ง‘๊ธฐ๋Š” ์˜ˆ์•ฝ์— ๋”ฐ๋ผ ์‹คํ–‰๋ฉ๋‹ˆ๋‹คโ€”โ€”์ด ์ €์žฅ์†Œ๋ฅผ ๋‹ค๋ฃจ๊ฒŒ ๋˜๋ฉด ๋‹ค์‹œ ํ™•์ธํ•˜์„ธ์š”.