Xingjian Shi (@sxjscience) profile picture
United States
Joined July 2015
Xingjian Shi retweeted
Boson AI's new audio generation model is out: emotionally expressive voice, long form audio, multi-speaker cloning, directable audio (e.g. music, laughter), trained on 10M+ hours of audio, and best of all, open source. boson.ai/blog/higgs-audio-v2 - @boson_ai @sxjscience @mli65
7
6
2
36
6,140
We are hiring at all levels! If you are interested, ping me through twitter or send an email to the address shown in our #ACL2023NLP paper: arxiv.org/pdf/2305.09651.pdf
We're hiring for Boson AI. Talk to @sxjscience at #ACL2023 if you want to work on language alignment, finetuning, infrastructure and serving, statistical modeling, optimization, model evaluation, and data.
1
1
431
Xingjian Shi retweeted
We're hiring for Boson AI. Talk to @sxjscience at #ACL2023 if you want to work on language alignment, finetuning, infrastructure and serving, statistical modeling, optimization, model evaluation, and data.
1
1
1
6
3,540
See you at Frontenac Ballroom and Queen’s Quay! #ACL2023 #ACL2023NLP
LGTM😉 Learn good teacher matters! Excited to present our #ACL2023 paper on learning to teach for knowledge distillation. Talk to you soon in poster session 2, 14:00-15:30 (EDT). Arxiv: arxiv.org/abs/2305.09651 Code: github.com/twinkle0331/LGTM Video+slides: virtual2023.aclweb.org/paper…
2
356
Check out LeMDA! Plug-and-play augmentation for multimodal data. Learns “hard but reasonable” ways to permute the features.
1
5
2,874