1 citations · 1 across the 10 of their papers we have counts for
11 papers
VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning
Haoze Li, Peng Zhou, Peiyuan Wu +2
Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a group fails w…
SpecLoop: An Agentic RTL-to-Specification Framework with Formal Verification Feedback Loop
Fu-Chieh Chang, Yu-Hsin Yang, Hung-Ming Huang +5
RTL implementations frequently lack up-to-date or consistent specifications, making comprehension, maintenance, and verification costly and error-prone. While prior work has explor…
Assessing Large Language Models in Generating RTL Design Specifications
Hung-Ming Huang, Yu-Hsin Yang, Fu-Chieh Chang +5
As IC design grows more complex, automating comprehension and documentation of RTL code has become increasingly important. Engineers currently should manually interpret existing RT…
Research on intelligent generation of structural demolition suggestions based on multi-model collaboration
Zhifeng Yang, Peizong Wu
The steel structure demolition scheme needs to be compiled according to the specific engineering characteristics and the update results of the finite element model. The designers n…
Unveiling the Latent Directions of Reflection in Large Language Models
Fu-Chieh Chang, Yu-Ting Lee, Pei-Yuan Wu
Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, mos…
A Theoretical Framework for OOD Robustness in Transformers using Gevrey Classes
Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu
We study the robustness of Transformer language models under semantic out-of-distribution (OOD) shifts, where training and test data lie in disjoint latent spaces. Using Wasserstei…
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Yu-Ting Lee, Fu-Chieh Chang, Yu-En Shu +2
Intrinsic moral self-correction refers to the phenomenon where a language model refines its ethical judgments or aligns its outputs purely through prompting. While effective across…
Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures
Fu-Chieh Chang, You-Chen Lin, Pei-Yuan Wu
Large language models (LLMs) have demonstrated remarkable mathematical capabilities, largely driven by chain-of-thought (CoT) prompting, which decomposes complex reasoning into ste…
RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner
Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih +2
The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT…
Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning
Yen-Ru Lai, Fu-Chieh Chang, Pei-Yuan Wu
Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especi…
CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network
Jia-Hau Bai, Chi-Ting Liu, Yu Wang +2
This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under…