Alissa O. @alissa_OS

MLT student @LTIatCMU @tsvetshop | B.S. Computer Science & Mathematics @WPI Joined July 2021

Tweets

17
Followers

134
Following

141
Likes

221

Jon Soucy @jrsoucy

a year ago

Honored to be a part of this year’s cohort Rising Stars! Thank you @BostonU_BME @ColumbiaBME @JHUBME @CornellBME for organizing such an amazing event!

Boston University Biomedical Engineering @BostonU_BME

a year ago

Honored to be a part of this year’s cohort Rising Stars! Thank you @BostonU_BME @ColumbiaBME @JHUBME @CornellBME for organizing such an amazing event!

0 20 87 42K 5

Download Image

0 3 22 2K 0

Very excited to share our recent work to improve cell replacement therapies for restoring vision lost to glaucoma and other optic neuropathies! @BaranovLab @Levi_J_Todd @HMSeye @MassEyeAndEar pnas.org/doi/10.1073/pn…

1 6 13 3K 1

Vijay V. @vijaytarian

2 years ago

LLM APIs let you build NLP systems in seconds; just write a prompt and use it as you wish. But APIs cost money and have privacy concerns. Our new library Prompt2Model turns a prompt into a small expert model that can match LLM performance but runs locally! github.com/neulab/prompt2…

5 49 161 80K 61

Sachin Kumar @shocheen

2 years ago

📢 I am excited to share that I will be starting as an Assistant Professor @OhioState @OhioStateCSE in Fall 2024 🥳. Before that, I will spend a year as a postdoc in the @ai2_allennlp team @allen_ai!

34 20 311 37K 15

Vijay V. @vijaytarian

2 years ago

Text clustering is widely used but unpredictable, because there are many "right" ways to cluster data. Semi-supervised clustering tries to solve this, but too often it requires a lot of user feedback to be useful. We explore the problem of “few-shot clustering” using LLMs.

2 41 231 50K 120

Download Image

Clara Na @claranahhh

3 years ago

Excited to share our paper (w/ @sanketvmehta & @strubell), "Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models," to appear at #EMNLP2022 Findings (will be presented at SustaiNLP 2022)! Paper here 👉 arxiv.org/abs/2205.12694 🧵👇 (1/n)

4 35 169 0 35

Download Image

thamar | @thamar_solorio

3 years ago

It really takes a village of wonderful, responsible, and creative volunteers to pull together such an amazing 60th edition of the ACL. THANK YOU! i enjoyed meeting people and hearing about all the exciting research happening #acl2022 @AlineVillav @preslav_nakov @SmaraMuresanNLP

0 4 33 0 0

Download Image

Alissa O. @alissa_OS

4 years ago

Why dabble in NLP tasks like “joke explanation” knowing that a model has “potential… to falsely affirm stereotypes”? (PaLM 👀)

0 0 2 0 0

Vijay V. @vijaytarian

4 years ago

This project was joint work with @Sid_Arora_18, Alissa Ostapenko and @siddalmia05, and advised by Florian Metze, Shinji Watanabe, and Alan W Black, all from @LTIatCMU. (9/9)