Shunchang Liu

Shunchang

AI & ML interests

AI

Recent Activity

authored a paper 18 days ago

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

updated a model 23 days ago

Shunchang/sae-rm-checkpoints

updated a model 2 months ago

Shunchang/sae-rm-checkpoints

View all activity

Organizations

None yet

Papers 1

arxiv:2605.16339

models 5

Shunchang/sae-rm-checkpoints

Feature Extraction • Updated 23 days ago

Shunchang/SmolVLM-Instruct-condition

Updated May 26, 2025 • 1

Shunchang/SmolVLM-Base-condition

Updated May 19, 2025 • 2

Shunchang/SmolVLM-Base-condition-condition

Updated May 19, 2025

Shunchang/tmp

Updated May 19, 2025

datasets 3

Shunchang/sae-rm-perturbation-data

Preview • Updated May 7 • 17

Shunchang/hh-rlhf-labeled

Viewer • Updated Aug 27, 2025 • 339k • 7

Shunchang/hh-rlhf-all-text

Viewer • Updated Aug 27, 2025 • 339k • 8