Yoav Wald
@wald_yoav
Followers
253
Following
560
Statuses
58
Faculty fellow @NYUDataScience. ML safety, causal inference, healthcare applications.
New York
Joined February 2021
What prompt generated the image on the right? Come find out today at our tutorial on OOD generalization: Shortcuts, Spuriousness, and Stability @Maggiemakar @aahladpuli Panel: @ElanRosenfeld @AdtRaghunathan Danica Sutherland
0
5
19
RT @MichaelOberst: I'm recruiting PhD students for Fall 2025! CS PhD Deadline: Dec. 15th. I work on safe/reliable ML and causal inference,…
0
128
0
RT @zacharylipton: Unpacking what's going on in our paper on Med-* foundation models & their failure to improve over their generic counterp…
0
10
0
RT @NogaZaslavsky: I'm recruiting PhD students this cycle! My lab works at the intersection of information theory, cognition, language, and…
0
102
0
RT @ARSaporta: Multimodal representation learning works for 2 modalities, but what if you're working with 3+ modalities, like in healthcare…
0
57
0
RT @suchisaria: Will your LLM model generalize over time or across sites? How do we improve robustness? This is a key issue LLMs struggle w…
0
5
0
@ninoscherrer @AmirFeder @causalclaudia @suchisaria @amir_feder Oh no! Failing to acknowledge Amir + exposing my horrible tweeting skills... Thanks for the handle :)
0
0
0
Also, better late than never, yesterday @aahladpuli presented his cool work about shortcut learning in perception tasks. Some nice insights about useful inductive biases in these tasks.
0
0
1
RT @Maggiemakar: Happy to announce that I'm looking for PhD candidates to join my lab @UMichCSE this year! If you're interested in workin…
0
24
0
RT @kchonyc: a very interesting observation: all you need is perceptron 🤣 by @aahladpuli @lilyhzhang Yoav Wald &…
0
11
0
RT @Zalmanson: Thank you @ERC_Research for this amazing grant- I will work hard (with and without the algorithms’ help) on these topics for…
0
4
0
RT @elliot_creager: Once more, in verbose mode: as of today I am an Assistant Professor @WaterlooENG (ECE dept), and faculty affiliate @Vec…
0
27
0
This comes up in monitoring safety, where novel types of data necessitates a reevaluation of existing models. Under a "mild" assumption, we give a method + bounds on detecting the novel subgroup.
0
0
6
RT @ARGleave: Excited to be moderating panel on generalization, scaling and safety at #icml2023 with great panelists @sleepinyourhat @zacha…
0
8
0
Coming up next!
If you’re at #ICML2023 join me here: Giving an invited talk later today on AI Safety. Below are some of the papers our lab has written on the topic in last 5 yrs; this talk will give a brief overview and focus on learning/evaluation.
2
1
4
RT @ShalitUri: Our lab is hiring an ML in health PhD/postdoc! This is for an applied causal ML project, with very close collaboration with…
0
28
0