5 papers
On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models
Chee Heng Tan, Zhuoyi Lin, Mehul Motani +1
In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reasoning accuracy and verbalize i…
Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-Thought
Ching-Chieh Tsao, Zhuoyi Lin, Wenya Wang
Mixture-of-Experts architectures have revolutionized scaling, yet the underlying logic of their routing remains a black box. In this paper, we uncover a fundamental governing princ…
AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
Zhixuan Bao, Zhuoyi Lin, Jiageng Wang +5
Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generati…
Do Reviews Matter for Recommendations in the Era of Large Language Models?
Chee Heng Tan, Huiying Zheng, Jing Wang +5
With the advent of large language models (LLMs), the landscape of recommender systems is undergoing a significant transformation. Traditionally, user reviews have served as a criti…
A Spatial-Physics Informed Model for 3D Spiral Sample Scanned by SQUID Microscopy
J. Senthilnath, Jayasanker Jayabalan, Zhuoyi Lin +5
The development of advanced packaging is essential in the semiconductor manufacturing industry. However, non-destructive testing (NDT) of advanced packaging becomes increasingly ch…