Logan Engstrom @logan_engstrom

research @openai loganengstrom.com San Francisco, CA Joined September 2013

Tweets

316
Followers

2K
Following

351
Likes

2K

Andrew Ilyas @andrew_ilyas

2 months ago

“How will my model behave if I change the training data?” Recent(-ish) work w/ @logan_engstrom: we nearly *perfectly* predict ML model behavior as a function of training data, saturating benchmarks for this problem (called “data attribution”).

11 74 423 55K 410

Download Image

Andrew Ilyas @andrew_ilyas

5 months ago

Had a great time at @SimonsInstitute talking about new & upcoming work on meta-optimization of ML training tl;dr we show how to compute gradients *through* the training process & use them to optimize training. Immediate big gains on data selection, poisoning, attribution & more!

Logan Engstrom @logan_engstrom

6 months ago

9 32 175 33K 143

Download Image

1 3 32 6K 19

Gautam Kamath @thegautamkamath

6 months ago

Very cool work from Logan and the gang! One of these problems, indiscriminate data poisoning, has been one of my favorite mysteries in robustness -- and they did an order of magnitude better than we could previously! Looking forward to checking it out in more detail.

Logan Engstrom @logan_engstrom

6 months ago

9 32 175 33K 143

Download Image

0 1 9 3K 7

Andrew Ilyas @andrew_ilyas

11 months ago

After some very fun years at MIT, I'm really excited to be joining CMU as an assistant professor in Jan 2026! A big (huge!) thanks to my advisors (@aleks_madry @KonstDaskalakis), collaborators, mentors & friends. In the meantime, I'll be a Stein Fellow at Stanford Statistics.

27 15 564 56K 53

Logan Engstrom @logan_engstrom

12 months ago

Announcing a deadline extension for the ATTRIB workshop! Submissions are now due September 25th, with an option to submit October 4th if at least one paper author volunteers to be an emergency reviewer. More info here: attrib-workshop.cc

1 5 24 7K 5

Andrew Ilyas @andrew_ilyas

a year ago

The ATTRIB workshop is back @ NeurIPS 2024! We welcome papers connecting model behavior to data, algorithms, parameters, scale, or anything else. Submit by Sep 18! More info: attrib-workshop.cc Co-organizers: @tolgab0 @logan_engstrom @SadhikaMalladi @_elinguyen @smsampark

0 14 49 8K 15

Download Image

Andrew Ilyas @andrew_ilyas

a year ago

Thanks to all who attended our tutorial "Data Attribution at Scale" at ICML (w/ @smsampark @logan_engstrom @kris_georgiev1 @aleks_madry)! We're really excited to see the response to this emerging topic. Slides, notes, ICML video: ml-data-tutorial.org Public recording soon!

2 27 156 13K 106

Download Image

Logan Engstrom @logan_engstrom

a year ago

Stop by our poster on model-aware dataset selection at ICML! Location/time: 1:30pm Hall C 4-9 #1010 (Tuesday) Paper: arxiv.org/abs/2401.12926 with: @axel_s_feldmann @aleks_madry

6 6 40 4K 14

Aleksander Madry @aleks_madry

a year ago

At #ICML2024 ? Our tutorial "Data Attribution at Scale" will be to tomorrow at 9:30 AM CEST in Hall A1! I will not be able to make it (but will arrive later that day), but my awesome students @andrew_ilyas @smsampark @logan_engstrom will carry the torch :)

6 10 70 12K 23

Sarah Cen @cen_sarah

a year ago

In work w/ @andrew_ilyas @_JenAllen @hannahq_li @aleks_madry we give experimental evidence that users strategize on recommender systems! We find that users react to their (beliefs about) *algorithms* (not just content!) to shape future recs. Paper: arxiv.org/abs/2405.05596 1/8

3 17 97 32K 51

Download Image

Aleksander Madry @aleks_madry

a year ago

How is an LLM actually using the info given to it in its context? Is it misinterpreting anything or making things up? Introducing ContextCite: a simple method for attributing LLM responses back to the context: gradientscience.org/contextcite w/ @bcohenwang, @harshays_, @kris_georgiev1