Oscar Li @OscarLi101

Machine Learning PhD student @mldcmu Duke '19 BS in Math and CS Student researcher @google Past: applied scientist intern at Amazon @awscloud Pittsburgh, PA Joined February 2015

Tweets

169
Followers

263
Following

1K
Likes

954

Aviral Kumar @aviral_kumar2

5 days ago

Many LLM fine-tuning methods. Unclear what you should use & why? In our new paper, we did an extensive study of on-policy RL, supervised & offline contrastive methods (DPO, IPO) to answer this... 🧵⬇️ On-policy > offline, mode-seeking > mode-covering understanding-rlhf.github.io

3 65 270 32K 246

Download Image

Nathan Lambert @natolambert

2 weeks ago

Watch my @Stanford CS 25 lecture next week, "aligning open language models," it'll be good, v excited

25 96 622 138K 386

Download Image

Ahmad Beirami @abeirami

3 weeks ago

#icml2024 workshops list is up: icml.cc/virtual/2024/e…

1 11 56 12K 15

Michael Bronstein @mmbronstein

4 weeks ago

Gradient descent

18 24 488 21K 15

Download Image

Shubhendu Trivedi @_onionesque

a month ago

This has all the trappings of becoming a permanent reference. I have greatly admired the work of one of the authors for a long time. Nice to see this in book form! arxiv.org/abs/2403.14606

12 141 921 83K 945

Download Image

Soham De @sohamde_

a month ago

Just got back from vacation, and super excited to finally release Griffin - a new hybrid LLM mixing RNN layers with Local Attention - scaled up to 14B params! arxiv.org/abs/2402.19427 My co-authors have already posted about our amazing results, so here's a 🧵on how we got there!

12 62 318 45K 200

Graham Neubig @gneubig

4 months ago

I'm excited to be back in the classroom for CMU 11-711 Advanced NLP this semester! phontron.com/class/anlp2024/ We revamped the curriculum to take into account recent advances in LLMs, and we have a new assignment "build-your-own-LLaMa". We'll be posting slides/videos going forward.