Anqi Liu
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×1ML×1NLP×1
Frequent co-authors
Research Timeline
2026
Configurable Reward Model for Balanced Safety Alignment
The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM safety alignment across diverse and unseen safety configurations.
Toward Calibrated Mixture-of-Experts Under Distribution Shift
This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.LGEmpiricalRecentJun 18, 2026
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa +1 more
This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.
View →
cs.CLRecentMay 28, 2026