← Search

Huang Lei

2 accepted papers

2025

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

NeurIPS 2025poster

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rewards hinders the preference optimization based on Reinforcement Learning (RL) fo…

Cited by 0SourceScholar
2024

Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding

ACL 2024long

Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length,…