Ching-Yun Ko

Researcher, International Business Machines

Joined

July 2019

Names

Ching-Yun Ko

Emails

****@eee.hku.hk (Confirmed)

****@mit.edu (Confirmed)

****@ibm.com (Confirmed)

Personal Links

DBLP

Career & Education History

Researcher

International Business Machines (ibm.com)

2024 – Present

PhD student

Massachusetts Institute of Technology (mit.edu)

2019 – 2024

MS student

The University of Hong Kong (hku.hk)

2017 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Luca Daniel

2019 – 2024

MPhil Advisor

Ngai Wong

2017 – 2019

Expertise

Tensor decomposition

Present

Adversarial robustness

Present

Next generation language models

Present

Model alignment

Present

Publications

Patching LLMs Like Software: A Lightweight Method for Improving Safety Policies in Large Language Models
Huzaifa Arif, Pin-Yu Chen, Keerthiram Murugesan, Alex Gittens, Payel Das, Ching-Yun Ko
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Patching LLM like Software: A Lightweight Method for improving existing policy in Large Language Models
Huzaifa Arif, Keerthiram Murugesan, Ching-Yun Ko, Pin-Yu Chen, Payel Das, Alex Gittens
- Submitted to ICLR 2026
- Readers: Everyone
Large Language Models can Become Strong Self-Detoxifiers
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Youssef Mroueh, Soham Dan, Georgios Kollias, Subhajit Chaudhury, Tejaswini Pedapati, Luca Daniel
- ICLR 2025 Poster
- Readers: Everyone
MEMREASONER: A MEMORY-AUGMENTED LANGUAGE MODEL ARCHITECTURE FOR MULTI-HOP REASONING
Payel Das, Ching-Yun Ko, Sihui Dai, Georgios Kollias, Subhajit Chaudhury, Aurelie Lozano
- Submitted to ICLR 2025
- Readers: Everyone
MemReasoner: A Memory-augmented LLM Architecture for Multi-hop Reasoning
Ching-Yun Ko, Sihui Dai, Payel Das, Georgios Kollias, Subhajit Chaudhury, Aurelie Lozano
- Sys2-Reasoning Poster
- Readers: Everyone
On Robustness-Accuracy Characterization of Language Models using Synthetic Datasets
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Yung-Sung Chuang, Luca Daniel
- COLM
- Readers: Everyone
What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Jeet Mohapatra, Luca Daniel
- ICML 2024 Poster
- Readers: Everyone
On Robustness-Accuracy Characterization of Large Language Models using Synthetic Datasets
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Yung-Sung Chuang, Luca Daniel
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
SynBench: Evaluating Pretrained Representations for Image Classification using Synthetic Data
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Jeet Mohapatra, Luca Daniel
- Submitted to ICLR 2024
- Readers: Everyone
Sample-Specific Debiasing for Better Image-Text Models
Peiqi Wang, Yingcheng Liu, Ching-Yun Ko, William M Wells, Seth Berkowitz, Steven Horng, Polina Golland
- 12 Aug 2023
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 25 publications

Co-Authors

View all 37 co-authors