SI
Shawn Im
cs.LGcs.AIcs.CL
On Valency
published · living versionsW_t9xernyt·v1 · currentpublished
How Much Do Activation Monitors Benefit from Original Model Computations?
with James Oldfield, Jay J Culligan, Philip Torr, Sharon Li +1
1 version
Preprints & journals
4 papers in the corpus · 2024–2026How Much Do Activation Monitors Benefit from Original Model Computations?2610.24613v1 · James Oldfield, Shawn Im, Jay J Culligan et al.2026 · 0 citationsarXivon Valency
How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability2601.19208v2 · Shawn Im, Changdae Oh, Zhen Fang et al.2026 · 0 citationsarXiv
Visual Instruction Bottleneck Tuning2505.13946v2 · Changdae Oh, Jiatong Li, Shawn Im et al.2025 · 2 citationsarXiv
Can DPO Learn Diverse Human Values? A Theoretical Scaling Law2408.03459v5 · Shawn Im, Sharon Li2024 · 0 citationsarXiv
Career total: 6 works. 4 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.