Research Yushi Hu I'm a research scientist at meta superintelligence labs, where i work on building omni models that can understand and generate across many modalities (text, image, video, and more). i currently focus on rl post training these models. Yushi hu meta verified email at meta homepage natural language processing computer vision artificial intelligence.
Yushi Hu Introducing the olmoearth platform 🌍, state of the art ai paired with ready to use open infrastructure to turn earth data into clear, up to date… happy to share that i have started a new chapter. Semantic scholar profile for yushi hu, with 410 highly influential citations and 21 scientific research papers. Read yushi hu's latest research, browse their coauthor's research, and play around with their algorithms. Yushi hu (gs’11) received the b.a.sc. and m.a.sc. degrees from the university of waterloo, on, canada, in 2010 and 2012, respectively, where he is currently pursuing the ph.d. degree. he is also a lab instructor hardware specialist with the university of waterloo.
Yushi Hu Read yushi hu's latest research, browse their coauthor's research, and play around with their algorithms. Yushi hu (gs’11) received the b.a.sc. and m.a.sc. degrees from the university of waterloo, on, canada, in 2010 and 2012, respectively, where he is currently pursuing the ph.d. degree. he is also a lab instructor hardware specialist with the university of waterloo. meta cited by 3,769 natural language processing computer vision artificial intelligence. Yushi hu has 21 repositories available. follow their code on github. Yushi hu, weijia shi, xingyu fu, dan roth, mari ostendorf, luke zettlemoyer, noah a. smith, ranjay krishna published: 09 oct 2024, last modified: 09 oct 2024 neurips 2024 workshop on behavioral ml beyond thumbs up down: untangling challenges of fine grained feedback for text to image generation. In this work, we propose an effective training framework using fine grained rewards to teach llms to generate highly supportive and relevant citations, while ensuring the correctness of their responses.
Yushi Hu Yushi Hu Github meta cited by 3,769 natural language processing computer vision artificial intelligence. Yushi hu has 21 repositories available. follow their code on github. Yushi hu, weijia shi, xingyu fu, dan roth, mari ostendorf, luke zettlemoyer, noah a. smith, ranjay krishna published: 09 oct 2024, last modified: 09 oct 2024 neurips 2024 workshop on behavioral ml beyond thumbs up down: untangling challenges of fine grained feedback for text to image generation. In this work, we propose an effective training framework using fine grained rewards to teach llms to generate highly supportive and relevant citations, while ensuring the correctness of their responses.
Promptcap Prompt Guided Image Captioning Yushi hu, weijia shi, xingyu fu, dan roth, mari ostendorf, luke zettlemoyer, noah a. smith, ranjay krishna published: 09 oct 2024, last modified: 09 oct 2024 neurips 2024 workshop on behavioral ml beyond thumbs up down: untangling challenges of fine grained feedback for text to image generation. In this work, we propose an effective training framework using fine grained rewards to teach llms to generate highly supportive and relevant citations, while ensuring the correctness of their responses.
Promptcap Prompt Guided Image Captioning
Comments are closed.