AI for Science | Research Scientist @ Aresenale Bioyards | Prev Research Scientist @GeorgiaTech @NaverLabsEurope | PhD from @RITtigers | 🦋 also
USA
Joined June 2020
- Tweets321
- Following1K
- Followers866
- Likes2.6K
Pinned Tweet
Check out our latest collaborative paper comparing replay in biology to replay in artificial neural networks! @chriskanan
#artificalintelligence #continuallearning
Replay in Deep Learning: Current Approaches and Missing Biological Elements
pdf: arxiv.org/pdf/2104.04132.pdf
abs: arxiv.org/abs/2104.04132
"In this paper, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks"
Tyler Hayes retweeted
Following our @dagstuhl seminar on Continual Learning in the Foundation Model Era, we are now sharing a roadmap!
tldr: we view modular memory design as the missing piece to combine the capabilities of In-Weight & In-Context Learning for adaptation at scale
arxiv.org/abs/2603.01761
I'm excited to be giving a talk next week at #CoLLAs2025 on novel class discovery and open-vocabulary learning! 🐨
🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program!
These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.
👇 A thread introducing their work & talks.
#AI #MachineLearning #ContinualLearning #LifelongLearning
📢 Just one month left to submit!
Our Open World Anomaly Detection (OWAD) workshop is coming to #ICDM2025 this November in DC.
Topics include anomaly detection, continual learning, LLMs, and more.
📅 Submit by Aug 29
🔗 CfP: sites.google.com/view/icdm20…
#MachineLearning #AI
📢 OWAD @ IEEE ICDM 2025
🔍 Workshop on Open World Anomaly Detection in Dynamic and Evolving Environments
🗓️ Deadline: Aug 29, 2025
📍 Washington, DC
📚 Topics: anomaly detection, continual learning, & more
🌐 sites.google.com/view/icdm20…
#MachineLearning #AnomalyDetection #ICDM2025
The number of times I go to open the Duo Authenticator (2FA) app and default to opening Duolingo is higher than I would like to admit 🦉
I'm excited to announce that I’ve joined Georgia Tech as a Research Faculty Member and Research Scientist! 🐝
I’m thrilled to begin researching AI for Science. Here's to new challenges and opportunities ahead! 🎉
#AIforScience #GeorgiaTech #GoJackets
Tyler Hayes retweeted
I’m hiring 2 fully-funded PhD students to join our new Lifelong ML lab at the University of Bremen, where our mission is to make ML/AI more sustainable, adaptive, robust & inclusive.
Application deadline Dec. 10: uni-bremen.de/en/university/…
Please share & reach out with questions!
Tyler Hayes retweeted
🔥More Continual Learning meets Causality 🔥
In addition to our call for papers (by Nov 25), our Continual Causality Bridge at AAAI-25 has now opened the first continual confounding challenge!
Submit challenge solutions by Jan 7 on Kaggle! More info: continualcausality.org/chall…
The first “ConCon” challenge, tackling continual confounding, has just been launched!💡
Submit 3-page reports (non-archival) as part of the third Cont. Causal. Bridge at AAAI@2025. (Early deadline is Dec 6, 2024 AoE)
Check out the full announcement here: continualcausality.org/chall…
Tyler Hayes retweeted
📢 Job Alert 📢 @naverlabseurope
My team is looking for a Research Scientist in Visual Representation Learning - More info tinyurl.com/3jz935fk
Tyler Hayes retweeted
🌟 Keynote Spotlight from CoLLAs 2024 🌟
In "Lifelong Visual Representation Learning," Diane Larlus (@dlarlus) dives into continual learning for computer vision 🖼️ and explores how large pre-trained models are reshaping the field. She addresses challenges like catastrophic forgetting 🧠 and discusses methods to enable more robust, incremental learning 🔄✨.
📽️ Catch the full talk here: tinyurl.com/j847ytm9
#ComputerVision #LifelongLearning #AI #KeynoteSpeakers #CoLLAs2024
Tyler Hayes retweeted
Our Continual Causality Bridge is going into its 3rd edition at AAAI-25 @RealAAAI ! 🎉
Join us for a spectacular 2 days of continual learning & causality by submitting your original 4 page work (for proceedings or non-archival tracks) until Nov 25 AOE!
continualcausality.org/cfp/
Tyler Hayes retweeted
Using LLMs to explain why vision models fail in certain images, from colleagues at @naverlabseurope, recommended 😀
Tyler Hayes retweeted
We presented the poster at the eXCV workshop at #ECCV2024 . Thank you to people stopping by. If you missed it and you are interested in explainability in CV (#xAI) here is our poster.
New paper on arXiv today. We study the problem of explaining with simple sentences the errors made by computer vision models - to "debug" their performance into the wild. Work led by Gabriela Csurka, with @TylerLHayes and @dlarlus (amazing team 🚀)
Paper: arxiv.org/abs/2408.04471
Tyler Hayes retweeted
Our #ECCV2024 poster freshly up, and already some visitors! @mbsariyildiz and @WeinzaepfelP in action explaining our work on multiteacher distillation - see you at poster #10 !
Tyler Hayes retweeted
Want to distill diverse visual encoders into a universal one that outperforms all original ones?
Then check out our #ECCV2024 paper!
UNIC: Universal Classification Models via Multi-teacher Distillation
europe.naverlabs.com/unic
A quick summary 🧵
(1/6)
Tyler Hayes retweeted
🎉 Proceedings of the 1st @ContinualAI Unconference are out: proceedings.mlr.press/v249/
Papers followed a two-stage pre-registration process. Very refreshing to read about the positive & negative outcomes!
⭐️24 hours of amazing talks are also recorded here: youtube.com/playlist?list=PL…
Volume 249
Proceedings of the 1st ContinualAI Unconference
proceedings.mlr.press/v249
Is now available on PMLR
Tyler Hayes retweeted
I will present our study on Multilingual Retrieval-augmented generation, tomorrow at #ACL2024NLP workshop on Knowledgeable LLMs, 16:00 (poster hall)!
Come to discuss a multilingual extension of our BERGEN library: github.com/naver/bergen
arxiv.org/abs/2407.01463
#NLProc
Tyler Hayes retweeted
New paper on arXiv today. We study the problem of explaining with simple sentences the errors made by computer vision models - to "debug" their performance into the wild. Work led by Gabriela Csurka, with @TylerLHayes and @dlarlus (amazing team 🚀)
Paper: arxiv.org/abs/2408.04471
Tyler Hayes retweeted
If you're at #CoLLAs2024 do not hesitate to come and say hi, I'll be at poster 25 !
🚨Attending #CoLLAs2024 and want to learn more about novel class discovery for object detection!?
Then visit @dlarlus at our poster tomorrow: PANDAS: Prototype-based Novel Class Discovery and Detection! 🐼
Paper: arxiv.org/abs/2402.17420
Code: github.com/naver/pandas
