Dyah Adila

adila@wisc.edu

Profile Picture

Hello! I am a final-year PhD student advised by Fred Sala in the Sprocket Lab. I’ve been fortunate to intern at Google Research and AWS AI Labs.

I like understanding why things work (or don’t) inside LLMs, and turning those insights into efficient and reliable methods for adapting them.

I will be joining Scaled Cognition as a research scientist in June 2026 :blush:

See my CV

news

Mar 11, 2026 🌟 Our paper from my internship w/ Google Research last summer: Grow, Don’t Overwrite: Fine-tuning Without Forgetting is finally out! A very simple method that matches full fine-tuning on new tasks with almost zero forgetting.
Mar 3, 2026 🚨 Our new preprint, Weight Updates as Activation Shifts, is out! We move beyond trial-and-error by deriving a principled framework for activation steering. Code here.

selected publications

  1. Preprint
    Grow, Don’t Overwrite: Fine-tuning Without Forgetting
    Adila, Dyah, Mazzawi, Hanna, Dherin, Benoit, and Gonzalvo, Xavier
    In Preprint Mar 2026
    PDF
  2. Preprint
    Weight Updates as Activation Shifts: A Principled Framework for Steering
    Adila, Dyah, Cooper, John, Yun, Alexander, Trost, Avi, and Sala, Frederic
    In Preprint Mar 2026
    PDF
  3. Preprint
    Alignment, Simplified: Steering LLMs with Self-Generated Preferences
    Adila, Dyah, Shin, Changho, Zhang, Yijing, and Sala, Frederic
    In Preprint Jan 2025
    PDF
  4. ICML 2024
    Discovering Bias in Latent Space: An Unsupervised Debiasing Approach
    Adila, Dyah, Zhang, Shuai, Han, Boran, and Wang, Bernie
    In ICML 2024 Jul 2024
    PDF
  5. ICLR 2024
    Zero-Shot Robustification of Zero-Shot Models
    Adila, Dyah, Shin, Changho, Cai, Lingrong, and Sala, Frederic
    In ICLR 2024 May 2024
    PDF
  6. UAI
    Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
    Chen, Mayee F, Fu, Daniel Y, Adila, Dyah, Zhang, Michael, Sala, Frederic, Fatahalian, Kayvon, and Ré, Christopher
    In Proceedings of the conference on Uncertainty in artificial intelligence Aug 2022
    PDF

mentorship

I enjoy mentoring and collaborating with students. Some amazing undergrads I've worked with:

  • Alexander Yun — Weight Updates as Activation Shifts (Fall'25–Spring'26) → SWE at industry
  • Yijing Zhang — Alignment: Simplified (Fall'24–Spring'25) → Next: PhD at UW-Madison
  • Linrong (Chris) Cai — RoboShot (Fall'23–Spring'24) → Next: MSE at Princeton