#AFAA2026 #ICLR2026 | @zeyu1tang @prakhar_24 @adoubleva @miriamrateike @jamelleWD @gfarnadi @JessicaSchrouff @sanmikoyejo
Rio de Janeiro, Brazil
Joined August 2020
- Tweets178
- Following10
- Followers189
- Likes45
AFAA 2026 @ ICLR retweeted
🎉Our "Improving Bias Metrics in Vision-Language Models by Addressing Inherent Model Disabilities"📜 accepted @afciworkshop at #NeurIPS2024 W/ @BalajiDarur @GssKeerthireddy @ShashwatGoel7 🎉 #AlgorithmicFairness #Metrics #Evaluation #ProfGiri
📜Paper: precog.iiit.ac.in/pubs/NeurI…
👇🧵
AFAA 2026 @ ICLR retweeted
What's the best bias mitigation algorithm?
There isn't one!
Benchmarks often miss critical nuances. In our latest paper, we unpack these pitfalls. Critical work w/ @UsmanGohar , @luchengSRAI , @gfarnadi
🔥Spotlight @afciworkshop @ NeurIPS 2024
📰arxiv.org/pdf/2411.11101
AFAA 2026 @ ICLR retweeted
Come check out our spotlight work at Room 252 - Room 254 (Level 2) and let's talk more about fairness and distribution shifts :)
Amazing conversations at the morning poster session @afciworkshop
See you at the talk at 13:00 and the afternoon poster at 16:50 to 1730!
#NeurIPS2023
Improving Fairness-Accuracy tradeoff with a few Test Samples under Covariate Shift: arxiv.org/abs/2310.07535 (Spotlight)
A novel solution to ensure fairness under distribution shift, a Spotlight @ Algorithmic Fairness Workshop @afciworkshop @ 9:00 CST Fri 15 Dec.
(3/7)
AFAA 2026 @ ICLR retweeted
Very excited to be at #NeurIPS2023 to meet new friends, talk about NLP+society and get some career advice. Come check out my poster on Friday at the Algorithmic Fairness Through the Lens of Time workshop @afciworkshop
How do biases change before and after finetuning large scale visual recognition models? Our @afciworkshop paper incorporates sets of canonical images to highlight changes in biases for an array of off-the-shelf pretrained models. #NeurIPS2023
Link: arxiv.org/abs/2303.07615
AFAA 2026 @ ICLR retweeted
what an honor talking about the design of fairer architectures with @RheaSukthanker yesterday
today i’ll be applying this approach to *tabular data* and outperforming many traditional bias mitigations
stop by my poster in room 252 @afciworkshop #AFT2023
AFAA 2026 @ ICLR retweeted
Come join us! I’ll present a sneak peak of our work on auditing LMs through stigma-based lens. We just received notification that the work was accepted to #AAAI2024
🎉🎉🎉🎉
We are delighted to have invited talks by illustrious researchers @zemelgroup, @kunkzhang, @ioanauoft and Celestine Mendler-Dünner!
AFAA 2026 @ ICLR retweeted
Improving Fairness-Accuracy tradeoff with a few Test Samples under Covariate Shift: arxiv.org/abs/2310.07535 (Spotlight)
A novel solution to ensure fairness under distribution shift, a Spotlight @ Algorithmic Fairness Workshop @afciworkshop @ 9:00 CST Fri 15 Dec.
(3/7)
AFAA 2026 @ ICLR retweeted
#4: we designed fairer tabular models using our NAS+HPO approach to pareto dominate state-of-the-art bias mitigation methods
interestingly, we can do this *without taking a hit to the accuracy of the model*
📰 arxiv.org/abs/2310.12145
🏟️ @afciworkshop #AFT2023
with Richeek
AFAA 2026 @ ICLR retweeted
Check out @jaspreetranjit_ 's poster presentation at the @afciworkshop #NeurIPS2023 Workshop on her paper about the variation of gender biases in visual recognition models.
Paper: arxiv.org/pdf/2303.07615.pdf
Date: December 15th
Schedule and registration: afciworkshop.org/schedule
AFAA 2026 @ ICLR retweeted
Suppose one trains a sequence of models on an accumulating dataset, with new data labeled or generated by the most recent model.
How does the bias of the original dataset evolve over time? 🤔
A short extended abstract appearing at #NeurIPS2023's @afciworkshop
🧵⬇️
1/N
AFAA 2026 @ ICLR retweeted
𝗖𝗮𝘂𝘀𝗮𝗹 𝗗𝗲𝗽𝗲𝗻𝗱𝗲𝗻𝗰𝗲 𝗣𝗹𝗼𝘁𝘀
(for interpretable machine learning and xAI)
Here's a very short (3-min) talk recorder-v3.slideslive.com/#…
Preprint: arxiv.org/abs/2303.04209
Ask me anything about this here or at #NeurIPS2023 @afciworkshop
AFAA 2026 @ ICLR retweeted
That’s a wrap for AFCP 2022!!🎉
It was a pleasure hosting you at our 3rd edition of this workshop series on Algorithmic Fairness at NeurIPS!
Special thanks 🧵👇 1/6
AFAA 2026 @ ICLR retweeted
Thank you so much to our amazing speakers, panellists and roundtables leads for the enlightening talks and discussions
AFAA 2026 @ ICLR retweeted
Thank you to all the authors who presented their exciting papers at the workshop!!
AFAA 2026 @ ICLR retweeted
Thank you to all the reviewers and meta-reviewers who contributed their valuable time to give valuable feedback to authors and select the presented high quality work!
AFAA 2026 @ ICLR retweeted
Thank you to all attendees who joined us throughout the day for the lively discussions and sharing of idea around these important topics!
AFAA 2026 @ ICLR retweeted
Finally, a special shout out to our organizers @adoubleva, @miriamrateike, @gfarnadi, @nandofioretto, @JessicaSchrouff, Matt Kusner for their tireless work the past months to bring you this program. We hope you enjoyed the workshop!
AFAA 2026 @ ICLR retweeted
I'm excited to present my FIRST paper at the Algorithmic Fairness through the lens of Causality and Privacy Workshop #NeurIPS2022!
Looking forward to New Orleans! Reach out to chat about fairness, privacy, explainability, information theory...
arxiv.org/abs/2211.02139
AFAA 2026 @ ICLR retweeted
Super excited about the roundtables at the algorithmic fairness workshop! Join us on Saturday at noon, room 392!!
Join our in-person leads to discuss current challenges and open problems in:
Causality (@joftius, @rahmattalabi),
Privacy (@radcummings, @limufar, Sikha Pentyala)
Interpretability (@zacharylipton, @juliusadml, @amirhkarimi_)