Yavuz Faruk Bakman

Yavuz Faruk Bakman

PhD Student in Computer Science Capital One Responsible AI Fellow

University of Southern California

Biography

Welcome to my website! I’m a 4th year PhD student in Computer Science, co-advised by Salman Avestimehr and Sai Praneeth Karimireddy. Before starting my PhD, I worked at Hyperbee.ai as Research Engineer, focusing on making neural networks more efficient through compression and quantization. I got my Bachelor’s degree in Computer Science from Bilkent University, where I also researched machine learning security, specifically Trojan Attacks, with Professor Tudor Dumitras.

Currently, I’m interested in Reliable and Safe LLMs. I’m exploring uncertainty quantification of LLMs for reliable decision making and adversarial robustness of LLMs in continual learning scenarios. Furthermore, I have been doing research on LLM Efficiency, Reasoning, Continual Learning, Self-supervised Contrastive Learning and Federated Learning.

Outside of my research, I love playing video games, especially the Soulsborne series:

“Facing a challenge? Keep Calm and Git Gud.”

Interests
  • Reliable LLMs
  • Uncertainty Quantification
  • LLM Safety
  • LLM Interpretability
  • Efficient Reasoning
  • Continual Learning
  • Federated Learning
Education

  • PhD in Computer Science, Present

    University of Southern California, CA, US

  • MSc in Computer Science, 2025

    University of Southern California, CA, US

  • BSc in Computer Science, 2022

    Bilkent University, Turkey

Recent News

  • 09-25-2025: My internship work at Capital One “Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering” got accepted to Neurips ReliableML Workshop!

  • 09-20-2025: Our work “Reject Only Critical Tokens: Pivot-Aware Speculative Decoding” got accepted to Neurips Efficient Reasoning Workshop!

  • 09-15-2025: Our open-source library “TruthTorchLM” got accepted to EMNLP 2025!

  • 06-15-2025: Our Paper “Reconsidering Reconsidering LLM Uncertainty Estimation Methods in the Wild” got accepted to ACL 2025!

  • 06-15-2025: Our Paper “Un-considering Contextual Information: Assessing LLMs’ Understanding of Indexical Elements” got accepted to ACL 2025, Findings!

  • 05-02-2025: Our Library for assessing Truthfulness of LLMs, TruthTorchLM, officially released!

  • 02-02-2025: LARS got accepted to NAACL 2025, Findings!

  • 22-10-2024: I gave a talk at Amazon-USC Center on Secure and Trusted Machine Learning about Trustworthy and Efficient LLMs!

  • 20-10-2024: I have been selected as Capital One Responsible AI Fellow 2024 !

  • 01-07-2024: Our paper “CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning” got accepted to ECCV 2024 ! See you in Milano!

  • 28-06-2024: “Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts” got accepted to ACL Turkic Languages 2024 Workshop .

  • 16-06-2024: New paper “Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs” in collaboration with Amazon AI posted to Arxiv!

  • 16-05-2024: Our paper, “MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs” co-authored with Amazon AI, has been accepted to the ACL 2024.

  • 01-06-2024: Thrilled to announce that my first-author paper, “Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning,” has been accepted at ICLR 2024 . Looking forward to presenting our findings in Vienna!

  • 10-12-2023: I gave a talk at Amazon-USC Center on Secure and Trusted Machine Learning about Advancing Continual & Federated Learning with Self & Mixed Supervision.

  • 08-24-2022: Began my journey towards a PhD in Computer Science at University of Southern California(USC).

  • 06-15-2022: Graduated with the highest honors from Bilkent University, majoring in Computer Science.

  • 05-15-2022: Made the decision to join USC for my PhD studies under the guidance of Salman Avestimehr.

  • 04-14-2022: Honored to have received PhD offers from several prestigious institutions: Princeton , Cornell, USC, UCSB, UCSD, Wisconsin-Madison, and Northeastern.

Experience

 
 
 
 
 
Research Assistant
University of Southern California
September 2022 – Present California
Currently working on trustworthy LLM and how to keep LLMs up to date in terms of factual knowledge.
 
 
 
 
 
Research Engineer
Hyperbee.AI
June 2019 – September 2022 California
Worked on accelerating and compressing neural networks for various computer vision tasks including. Mostly focused on the quantization aspect.
 
 
 
 
 
Research Intern
University of Maryland, College Park
June 2021 – December 2021 Maryland
Attended TrojAI competetion in UMD - UC Berkeley Team supervised by Tudor Dumitras. Developed novel methods using loss surface, layer similarity and trojan transferability to detect backdoored models.

Recent Publications

Quickly discover relevant content by filtering publications.
Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Anil Ramakrishna, Chenyang Tao, Dimitrios Dimitriadis, Jieyu Zhao, Salman Avestimehr (2025). Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs. NAACL 2025, Findings.

PDF Cite

Erum Mushtaq, Duygu Nur Yaldiz, Yavuz Faruk Bakman, J Ding, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr (2024). CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning. ECCV 2024.

PDF Cite Code

Metehan Oguz, Y. Umut Ciftci, Yavuz Faruk Bakman (2024). Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts. ACL 2024 SIGTURK Workshop.

PDF Cite

Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr (2024). MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs. ACL 2024.

PDF Cite Code

Yavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin, Salman Avestimehr (2024). Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning. ICLR 2024.

PDF Cite Code

See all publications

Contact