Çağatay Yıldız

profpic.png

AI Research Building

Maria-von-Linden-Str. 6

72076 Tuebingen, Germany

I’m a postdoctoral researcher at the Bethge Lab, University of Tuebingen. During my doctoral studies, I was supervised by Harri Lähdesmäki at Aalto University, Finland. Before that, I worked with Taylan Cemgil in my Master’s degree at Bogazici University, Istanbul.

My postdoctoral studies are about a mixed bag of machine learning models. I work on

I’m supervising three MSc thesis:

  • diffusion models for sketch generation.
  • realistic online continual learning.
  • knowledge organization for continual question answering.

My name is super easy to pronounce: chaa-tai.

Check out Markus’ guideline for PhD students.

news

Feb 10, 2024 📝 Two papers submitted to CoLLAs 2024: Investigating Continual Pretraining in LLMs and Infinite dSprites for disentangled continual learning!
Dec 05, 2023 📜 I co-organized the first Tübingen pre-NeurIPS event.
Oct 28, 2023 👨‍💻 Modulated neural ODEs paper accepted to NeurIPS 2023!
Jul 27, 2023 🎤 Organized a summer school on ML and mathematical foundations in Bilimler Köyü.
Feb 06, 2023 🎤 Talks on PCA/VAEs and diffusion models in Nesin Village.
Nov 06, 2022 🥳 Latent diverge-free GP-ODE paper accepted to causal dynamics workshop at NeurIPS!
Oct 06, 2022 🥳 Interacting Dynamical Systems paper accepted to NeurIPS 2022!
Jul 23, 2022 🎤 Talk on continuous-time RL at ICML 2022 workshop on continuous-time methods.
Jun 17, 2022 🎤 Talk on neural ODEs at Nordic Probabilistic AI School. Lecture material here.
Jun 01, 2022 👨‍💻 Starting as a postdoc in Bethge Lab in Tuebingen!

latest posts

Mar 17, 2024 Sınırların ötesi
Apr 05, 2021 Bireysellesme
Aug 31, 2017 Okuduklarimdan Notlar

selected publications

  1. submitted
    Investigating Continual Pretraining in Large Language Models: Insights and Implications
    Çağatay Yıldız ,  Nishaanth Kanna Ravichandran ,  Prishruit Punia , and 2 more authors
    In Lifelong Learning Agents , 2024
  2. submitted
    Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
    Sebastian Dziadzio ,  Çağatay Yıldız ,  Gido Ven , and 3 more authors
    In Lifelong Learning Agents , 2024
  3. NeurIPS
    Invariant Neural Ordinary Differential Equations
    Ilze Amanda Auzina ,  Çağatay Yıldız ,  Sara Magliacane , and 2 more authors
    In Advances in Neural Information Processing Systems , 2023
  4. ICLR
    Latent Neural ODEs with Sparse Bayesian Multiple Shooting
    Valerii Iakovlev ,  Çağatay Yıldız ,  Markus Heinonen , and 1 more author
    In International Conference on Learning Representations , 2023
  5. NeurIPS
    Learning Interacting Dynamical Systems with Latent Gaussian Process ODEs
    Çağatay Yıldız ,  Melih Kandemir ,  and  Barbara Rakitsch
    In Advances in Neural Information Processing Systems , 2022
  6. UAI
    Variational multiple shooting for Bayesian ODEs with Gaussian processes
    Pashupati Hedge ,  Çağatay Yıldız ,  Harri Lahdesmaki , and 2 more authors
    In Uncertainty in Artificial Intelligence , 2022
  7. thesis
    Differential Equations for Machine Learning
    Çağatay Yıldız
    2022
  8. ICML
    Continuous-time Model-based Reinforcement Learning
    Çağatay Yıldız ,  Markus Heinonen ,  and  Harri Lahdesmaki
    In International Conference on Machine Learning , 2021
  9. NeurIPS
    ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
    Çağatay Yıldız ,  Markus Heinonen ,  and  Harri Lahdesmaki
    In Advances in Neural Information Processing Systems , 2019
  10. ICML
    Learning unknown ODE models with Gaussian processes
    Markus Heinonen ,  Çağatay Yıldız ,  Henrik Mannerström , and 2 more authors
    In International Conference on Machine Learning , 2018
  11. ICML
    Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
    Umut Simsekli ,  Çağatay Yıldız ,  Than Huy Nguyen , and 2 more authors
    In International Conference on Machine Learning , 2018