1 citations · 1 across the 7 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Zehao Jin, Ruixuan Deng, Junran Wang
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A…
cs.AI2026
Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Zehao Jin, Junran Wang, Ruixuan Deng +4
An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing: contro…