Polina Kirichenko (@polkirichenko) / X

Polina Kirichenko

297 posts

Polina Kirichenko

@polkirichenko

Research Scientist at FAIR @AIatMeta & visiting researcher at Princeton @VisualAILab prev. PhD at New York University 🇺🇦

New York City, NY

polkirichenko.github.io

Joined November 2018

Pinned
Polina Kirichenko
@polkirichenko
Jun 16, 2025
Excited to release AbstentionBench -- our paper and benchmark on evaluating LLMs’ *abstention*: the skill of knowing when NOT to answer! Key finding: reasoning LLMs struggle with unanswerable questions and hallucinate! Details and links to paper & open source code below! 🧵1/9
133K
Polina Kirichenko
@polkirichenko
Apr 7, 2022
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. ERM learns multiple features that can be reweighted for SOTA on spurious correlations, reducing texture bias on ImageNet, & more! w/ @Pavel_Izmailov and @andrewgwils arxiv.org/abs/2204.02937 1/11
Polina Kirichenko
@polkirichenko
Dec 8, 2023
Excited to share our #NeurIPS paper analyzing the good, the bad and the ugly sides of data augmentation (DA)! DA is crucial for computer vision but can introduce class-level performance disparities. We explain and address these negative effects in: openreview.net/pdf?id=yageaKl… 1/9
76K
Polina Kirichenko
@polkirichenko
May 2, 2025
We are hiring a PhD research intern at FAIR w/ @marksibrahim @kamalikac to start this summer or Fall! Potential topics: trustworthy and reliable LLMs, multi-modal LLMs and agents, post-training, reasoning, with a focus on open science/sharing our findings in the paper at the end
55K
Polina Kirichenko
@polkirichenko
Jun 4, 2024
I recently defended my PhD thesis and graduated from NYU! 🎉 Thank you so much to my committee members @andrewgwils @sainingxie @mengyer @Qi_Lei_ @orussakovsky @rob_fergus (sadly I forgot to take a common zoom picture) Happy graduation photos below! 👩‍🎓
55K
Polina Kirichenko
@polkirichenko
Jun 16, 2020
Why Normalizing Flows Fail to Detect Out-of-Distribution Data arxiv.org/abs/2006.08545 We explore the inductive biases of normalizing flows based on coupling layers in the context of OOD detection (1/6)
arxiv.org
Why Normalizing Flows Fail to Detect Out-of-Distribution Data
Detecting out-of-distribution (OOD) data is crucial for robust machine learning systems. Normalizing flows are flexible deep generative models that often surprisingly fail to distinguish between...
Polina Kirichenko
@polkirichenko
Jun 25, 2021
Excited to share that (1) It is my birthday 🎂 (2) We have a new paper "Task-agnostic Continual Learning with Hybrid Probabilistic Models" on arxiv today! We design a hybrid generative-discriminative model based on normalizing flows for continual learning arxiv.org/abs/2106.12772
Polina Kirichenko
@polkirichenko
Jul 17, 2022
We are excited to present our breakout session on robustness to distribution shift at @WiMLworkshop @icmlconf together with @shiorisagawa @LotfiSanae! Join our session & discussion tomorrow, Monday July 18, at 11am at the Exhibit Hall G at Level 100 Exhibition Halls 🙂 #ICML2022
Polina Kirichenko
@polkirichenko
Dec 8, 2020
We will be presenting "Why Normalizing Flows Fail to Detect Out-of-Distribution Data" at @NeurIPSConf tomorrow at 12 EST! neurips.cc/virtual/2020/p…
Polina Kirichenko
@polkirichenko
Jun 16, 2020
Why Normalizing Flows Fail to Detect Out-of-Distribution Data arxiv.org/abs/2006.08545 We explore the inductive biases of normalizing flows based on coupling layers in the context of OOD detection (1/6)
Polina Kirichenko
@polkirichenko
May 3, 2023
Come see our paper "Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations" at #ICLR2023 (notable-top-25%)! Spotlight talk on Wed 10:10am Oral 6 Track 5 and poster session 6 at 10:30am! (joint work w/ @Pavel_Izmailov @andrewgwils)
Polina Kirichenko
@polkirichenko
Apr 7, 2022
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. ERM learns multiple features that can be reweighted for SOTA on spurious correlations, reducing texture bias on ImageNet, & more! w/ @Pavel_Izmailov and @andrewgwils arxiv.org/abs/2204.02937 1/11
27K
Polina Kirichenko
@polkirichenko
Jul 17, 2022
I’m in Baltimore for #ICML2022! Really excited to attend the first in-person conference in a few years, connect with people and meet old friends! Ping me if you want to grab coffee or chat about research in deep learning robustness or other topics 🙂
Polina Kirichenko
@polkirichenko
Dec 1, 2021
💯 I will add my two cents here as a Russian student on F-1 visa in the US. While a PhD program typically takes 5-6 years (which is also indicated in all the legal documents, school invitation etc), Russian citizens can only get a student F-1 visa for 1 YEAR max!! 🤯😭 1/🧵
This post is unavailable.
Polina Kirichenko
@polkirichenko
Nov 28, 2022
Excited to be in New Orleans for #NeurIPS2022! Ping me if you want to grab coffee or lunch and chat about distribution shift, robustness, OOD generalization, jazz and other topics! 1/2
Polina Kirichenko
@polkirichenko
Jul 12, 2020
Excited to lead a breakout session on Uncertainty in Deep Learning at WiML Un-Workshop @icmlconf tomorrow, July 13 at 6:35pm GMT (2:35pm EDT)! Together with @MelaniePradier and Weiwei Pan
WiML
@WiMLworkshop
Jul 9, 2020
Our forth and final breakout session at the #WiML2020 Un-Workshop co-located with #ICML2020 will take place Monday, July 13 at 6:35PM – 7:35PM GMT. More information about the breakout sessions here: tinyurl.com/yd3apep6 #WiML2020 #ICML2020 #WiML #machinelearning @icmlconf