Scholar

Kwan Ho Ryan Chan

Google Scholar ID: DBXWBqcAAAAJ

University of Pennsylvania

Deep learningExplainable AIInterpretabilitySelf-Supervised LearningMachine Learning

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

656

H-index

11

i10-index

12

Publications

20

Co-authors

32

list available

Contact

CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗

Publications

7 items

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

2025

Cited

0

Conformal Information Pursuit for Interactively Guiding Large Language Models

2025

Cited

0

IP-CRR: Information Pursuit for Interpretable Classification of Chest Radiology Reports

2025

Cited

0

Concept Lancet: Image Editing with Compositional Representation Transplant

2025

Cited

0

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

2025

Cited

0

Do LLMs "know" internally when they follow instructions?

arXiv.org · 2024

Cited

1

Learning Interpretable Queries for Explainable Image Classification with Information Pursuit

arXiv.org · 2023

Cited

2

Resume (English only)

Academic Achievements

Recipient of Penn Engineering Dean’s Fellowship
Recipient of NSF Graduate Research Fellowship (NSFGRFP)
Paper “Do LLMs ‘know’ internally when they follow instructions?” accepted to ICLR 2025 (Jan 2025)
Paper “PaCE: Parsimonious Concept Engineering for Large Language Models” accepted to NeurIPS 2024 (Sep 2024)
Two papers accepted to NeurIPS (Sep 2025)
Passed candidacy exam (Oct 2025)

Co-authors

32 total

Director of School of Computing & Data Science, HKU; Visiting Professor of EECS, Berkeley

University of California, Berkeley

Rachleff University Professor, University of Pennsylvania; Amazon Scholar; Chief Scientist, NORCE

Google DeepMind

Aditya Chattopadhyay

Johns Hopkins University

Electrical Engineering, Columbia University

University of Pennsylvania