Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
portfolio
projects
🚗 OutVenture: In-Car Educational AR Chatbot System
Published:
An interactive in-car multimodal AR chatbot for outside landmark explanations through vision and speech.
🧩 Senior Thesis Project: Federated Learning Algorithm Exploiting Consensus ADMM for Enhanced Non-Convex Optimization
Published:
FedGP: Gradient Prediction for Faster Federated Learning
🧠 TruthTorchLM: A Comprehensive Library for Truthfulness Assessment in LLMs
Published:
An open-source toolkit with 30+ truth methods for evaluating and predicting the truthfulness of LLM outputs.
publications
Reconsidering LLM Uncertainty Estimation Methods in the Wild
Published in ACL 2025, 2025
📄 Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang, Tuo Zhang, Baturalp Buyukates, Salman Avestimehr, Sai Praneeth Karimireddy,
Reconsidering LLM Uncertainty Estimation Methods in the Wild ACL 2025
Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
Published in preprint, 2025
📄 Jisoo Kim, Sungmin Kang, Sunwoo Lee, _Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning_
preprint
GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
Published in preprint, 2025
📄 Sungmin Kang, Jisoo Kim, Salman Avestimehr, Sunwoo Lee, _GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation_
preprint
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
Published in EMNLP 2025 System Demonstrations, 2025
📄 Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sungmin Kang, Alperen Öziş, Hayrettin Eren Yildiz, Mitash Ashish Shah, Zhiqi Huang, Anoop Kumar, Alfy Samuel, Daben Liu, Sai Praneeth Karimireddy, Salman Avestimehr, _TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs_
EMNLP 2025 System Demonstrations
talks
Federated Learning Implementation through Socket Communication
Published:
Invited Lecture in course ‘Artificial Intelligence Communications’ by Professor Hongseok Kim, at Sogang University
GitHub
Poster Presentation, “Reconsidering LLM Uncertainty Estimation Methods in the Wild”, at ACL 2025
Published:
Poster Presentation, “Reconsidering LLM Uncertainty Estimation Methods in the Wild”, at ACL 2025
USC ECE Annual Research Festival
Published:
Presented a poster at the USC ECE Annual Research Festival and was awarded the Best Poster Award!