Shunchang Liu

Shunchang

https://shunchang-liu.github.io/

AI & ML interests

AI

Recent Activity

upvoted a paper 2 days ago

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders

authored a paper 4 days ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

upvoted a paper 4 days ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

View all activity

Organizations

None yet

Shunchang 's datasets 4

Shunchang/multimodal-em-data

Viewer • Updated 19 days ago • 8.47k • 510

Shunchang/sae-rm-perturbation-data

Preview • Updated May 7 • 66

Shunchang/hh-rlhf-labeled

Viewer • Updated Aug 27, 2025 • 339k • 16

Shunchang/hh-rlhf-all-text

Viewer • Updated Aug 27, 2025 • 339k • 28