Aliyah R. Hsu

profile.JPG

Pronouns: she/her

Hi there! I am an Applied Scientist at Salesforce AI, dedicated to advancing the capabilities of autonomous systems. My current work focuses on agentic workflow optimizations, reasoning model fine-tuning, and engineering RL frameworks to enable continuous learning in agents.

Previously, I was a PhD student at UC Berkeley’s EECS department and BAIR, advised by Bin Yu. My doctoral research spanned NLP, interpretability, and AI-assisted clinical decision-making, with a core focus on building trust and safety for neural networks in high-stakes domains.


🎓 Education & Honors

  • PhD in EECS, UC Berkeley (Chancellor Fellowship & EECS Excellence Award)
  • Double B.S. in Electrical Engineering & Economics, National Taiwan University (NTU)

🔬 Research Roots

Before Salesforce and Berkeley, I collaborated with Lin-Shan Lee, Hung-Yi Lee, and Yu-Chiang Frank Wang on dialogue response generation and computer vision.

news

Jun 6, 2025 Our paper CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents building a reliable agentic workflow for clinical decision rule selection and execution with experts in the loop was accepted to AMIA 2025 Annual Symposium for presentation AND part of the Symposium On Demand Recording! :sparkles:
Mar 5, 2025 Our paper Enhancing CBMs Through Binary Distillation with Applications to Test-time Intervention decomposing Concept Bottleneck Models(CBMs) predictions into interpretable binary-concept-interaction attributions to guide adaptive test-time intervention got into ICLR 2025 BuildingTrust Workshop :sparkles:
Jan 22, 2025 Our paper Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition proposing a novel circuit discovery algorithm for more efficient mechanistic interpretability in large language models got into ICLR 2025 :sparkles:
May 20, 2024 Returned to Salesforce Einstein Language Intelligence Data Science Team as an Applied Scientist Intern again! :smiley:
May 7, 2024 Will be attending ICLR 2024 at Vienna, Austria!