Skip to main content

๐Ÿข NVIDIA Research

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
·2682 words·13 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Natural Language Processing Large Language Models ๐Ÿข NVIDIA Research
AceMath๋Š” ์‚ฌ์ „ ํ›ˆ๋ จ ๋ฐ ๋ณด์ƒ ๋ชจ๋ธ๋ง์„ ํ†ตํ•ด ์ตœ์ฒจ๋‹จ ์ˆ˜ํ•™ ์ถ”๋ก  ๋Šฅ๋ ฅ์„ ๋‹ฌ์„ฑํ•œ ํ”„๋Ÿฐํ‹ฐ์–ด๊ธ‰ ๋ชจ๋ธ ์‹œ๋ฆฌ์ฆˆ์ž…๋‹ˆ๋‹ค.
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
·2277 words·11 mins· loading · loading
AI Generated ๐Ÿค— Daily Papers Multimodal Learning Vision-Language Models ๐Ÿข NVIDIA Research
ResGen, ๊ณ ํ’ˆ์งˆ ์ƒ์„ฑ๊ณผ ๋น ๋ฅธ ์ƒ˜ํ”Œ๋ง ์†๋„๋ฅผ ๋ชจ๋‘ ๋‹ฌ์„ฑํ•˜๋Š” ํšจ์œจ์ ์ธ RVQ ๊ธฐ๋ฐ˜ ์ƒ์„ฑ ๋ชจ๋ธ.