Yining (Sam) Huang 🧬

Yining (Sam) Huang

(he/him)

CS PhD Student

University of Pennsylvania

About

I’m a Computer Science PhD student at the University of Pennsylvania, working on AI agents and deep research systems. I’m also interested in AI for science, particularly RNA and protein design.

I earned my master’s in Biomedical Informatics at Harvard Medical School and my bachelor’s in Computer Science and Statistics at Northwestern University. I’ve also worked as a research intern at Qwen in summer 2026.

Education

PhD Computer Science

2025-08

University of Pennsylvania

MS Biomedical Informatics

2023-08
2025-05

Harvard Medical School

BS Computer Science & Statistics

2019-09
2023-06

Northwestern University

Experience

Research Intern, Foundation Models

Qwen

Post-Training • Long-Horizon Agents

Graduate Research Assistant

Harvard Medical School

AI for Protein Design at Debbie Marks Lab.
Featured Publications
Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale featured image

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental …

Purely Agentic Black-Box Optimization for Biological Design featured image

Purely Agentic Black-Box Optimization for Biological Design

Many key challenges in biological design -- such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering -- can be framed as black-box …

Navigating Chemical Space with Latent Flows featured image

Navigating Chemical Space with Latent Flows

Recent progress of deep generative models in the vision and language domain has stimulated significant interest in more structured data generation such as molecules. However, …

Multi-Scale Representation Learning for Protein Fitness Prediction featured image

Multi-Scale Representation Learning for Protein Fitness Prediction

Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of functional annotations from wet-lab …

M²Hub: Unlocking the Potential of Machine Learning for Materials Discovery featured image

M²Hub: Unlocking the Potential of Machine Learning for Materials Discovery

We introduce M²Hub, a toolkit for advancing machine learning in materials discovery. Machine learning has achieved remarkable progress in modeling molecular structures, especially …

Recent Publications
Recent & Upcoming Talks
From Literature Overload to AI Research Partner: Deep Research Agents for Biology featured image

From Literature Overload to AI Research Partner: Deep Research Agents for Biology

avatar
Yining (Sam) Huang
•
Machine Learning-Driven High-Throughput Mapping of Lipid Nanoparticle Structure–Function Relationships for Ex-Vivo Immunotherapy featured image

Machine Learning-Driven High-Throughput Mapping of Lipid Nanoparticle Structure–Function Relationships for Ex-Vivo Immunotherapy

Agentic optimization to understand and design LNPs.

avatar
Yining (Sam) Huang
•