AIM-Harvard

university

https://aim.hms.harvard.edu

AIM-Harvard

Activity Feed Request to join this org

AI & ML interests

Artificial Intelligence in Medicine (AIM) Program (NLP group/Bitterman lab: https://www.bittermanlab.org/)

Recent Activity

shanchen authored a paper 21 days ago

MedBrowseComp: Benchmarking Medical Deep Research and Computer Use

shanchen authored a paper 21 days ago

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models

shanchen authored a paper 21 days ago

When Models Reason in Your Language: Controlling Thinking Trace Language Comes at the Cost of Accuracy

View all activity

Collections 1

spaces 1

Rabbits Leaderboard

Visualize LLM robustness in handling drug name synonyms

models 0

None public yet

datasets 30

AIM-Harvard/MedBrowseComp_Meta

Viewer • Updated May 22 • 442 • 48

AIM-Harvard/MedBrowseComp

Viewer • Updated May 22 • 1.14k • 439 • 7

AIM-Harvard/MedBrowseComp_CUA

Viewer • Updated May 13 • 484 • 19

AIM-Harvard/cardiffnlp_tweet_sentiment_multilingual_translated

Viewer • Updated Jan 10 • 6.09k • 19

AIM-Harvard/google_gemma_2_9b_it_boolq

Viewer • Updated Jan 9 • 3.27k • 35

AIM-Harvard/google_gemma_2_9b_boolq

Viewer • Updated Jan 9 • 3.27k • 33

AIM-Harvard/google_gemma_2_2b_boolq

Viewer • Updated Jan 9 • 3.27k • 40

AIM-Harvard/google_gemma_2_9b_it_piqa

Viewer • Updated Jan 9 • 1.84k • 34

AIM-Harvard/google_gemma_2_9b_piqa

Viewer • Updated Jan 9 • 1.84k • 34

AIM-Harvard/google_gemma_2_2b_piqa

Viewer • Updated Jan 9 • 1.84k • 33

View 30 datasets