Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Anqi Liu

Anqi Liu

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

ML×2AI×2NLP×2Robotics×1

Frequent co-authors

Zhengping Jiang2×
Mehran Khodabandeh2×
Akash Bharadwaj2×
Manik Bhandari2×
Mayur Srungarapu2×
Benjamin Van Durme2×

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.

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.

RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms

The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.ROEmpiricalRecentOct 23, 2026

RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms

Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu +4 more

The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.

View →
cs.AIcs.LGEmpirical
Recent
Jun 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

Configurable Reward Model for Balanced Safety Alignment

Zhengping Jiang, Mehran Khodabandeh, Akash Bharadwaj, Manik Bhandari +4 more

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 s…

View →
cs.CLRecentMay 28, 2026

Configurable Reward Model for Balanced Safety Alignment

Zhengping Jiang, Mehran Khodabandeh, Akash Bharadwaj, Manik Bhandari +4 more

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 s…

View →