Chhavi Yadav

(2/2)

Upon graduation,I paused to reflect on what my PhD had truly taught me.Was it just how to write papers,respond to brutal reviewer comments & survive w/o much sleep?Or did it leave a deeper imprint on me,beyond the metrics & milestones?Turns out, it did.

Read on 4 more: www.chhaviyadav.org/blogs 1/2

Congrats and all the best for your new chapter! 🎉🎊

Thanks Ioana for all your support!

Together, my research calls for a rethinking of what it means to be truly Trustworthy in a world shaped by conflicting incentives.
Defense Slides : bit.ly/chhavi_thesi...
(5/5)

My research aims to develop end-to-end Trustworthy AI solutions that account for these realities, I (1) examine how existing methods fail under incentive misalignment & (2) design end-to-end robust solutions using cryptographic approaches which account for said incentives. (4/n)

Trustworthy AI literature offers numerous solutions for desirable properties such as fairness, explainability & so on. Yet, many of these solutions fall short when deployed in the real-world which is rife with misaligned incentives between stakeholders (model trainers, data providers, customer)(3/n)

My research has been about designing Trustworthy AI solutions with real-world incentive structures in mind. While AI holds great promise for societal impact, it also poses serious risks, from reinforcing bias to compromising privacy. (2/n)

Successfully defended my thesis today!
Extremely grateful to my amazing advisor, #KamalikaChaudhuri, whose unwavering support, insights, teachings and motherly love made all this possible.. Also a big thanks to my committee members, #SanjoyDasgupta, #TaylorBerg-kirkpatrick & #TaraJavidi! (1/n)

Bringing to you my latest paper, to be presented at #ICML2025 this July -- ‘ExpProof : Operationalizing Explanations for Confidential Models with ZKPs’

Paper Link : arxiv.org/abs/2502.03773
Code : github.com/emlaufer/Exp...

Bringing to you my latest paper, to be presented at #ICML2025 this July -- ‘ExpProof : Operationalizing Explanations for Confidential Models with ZKPs’

Paper Link : arxiv.org/abs/2502.03773
Code : github.com/emlaufer/Exp...

Explainable and Interpretable AI: State of the Art Survey The goal of this survey is to understand the state of the art in explainable AI. Please answer the questions about one specific project where you used an XAI method. Your responses will be anonymized ...

We're conducting a survey on interpretability/explainability. If you are a researcher in XAI or use XAI tools in practice, please help us by filling this short survey!
RTs appreciated!

docs.google.com/forms/d/e/1F...

Explainable and Interpretable AI: State of the Art Survey The goal of this survey is to understand the state of the art in explainable AI. Please answer the questions about one specific project where you used an XAI method. Your responses will be anonymized ...

We're conducting a survey on interpretability/explainability. If you are a researcher in XAI or use XAI tools in practice, please help us by filling this short survey!
RTs appreciated!

docs.google.com/forms/d/e/1F...

Loving overleaf’s AI-based error assist! Works like magic!
Writefull on the other hand not so much, keeps giving bad suggestions :(

put in their heart and soul into creating something, the imperfections, the creativity and imagination.. what are your thoughts?

With so much AI-generated content in our lives, I find myself valuing human-generated content more & more. Eg. I still want to hang human-generated paintings in my room over ai-generated.
There is something about human generated content which connects with the heart.. That someone out there has

Yea probably do you have a link? New to this

Can someone share a list of the #ML people on here?