collaborators

6 papers

cs.LG2026

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

Xiaoyun Zhang, Xiaojian Yuan, Di Huang +6

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance…

cs.LG2026

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Yaoyu Zhu, Di Huang, Hanqi Lyu +16

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as…

cs.LG2026

LocalV: Exploiting Information Locality for IP-level Verilog Generation

Hanqi Lyu, Di Huang, Yaoyu Zhu +10

The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate compl…

cs.CL2025

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion

Yutong Wu, Di Huang, Ruosi Wan +8

Autoformalization aims to translate natural-language mathematical statements into a formal language. While LLMs have accelerated progress in this area, existing methods still suffe…

cs.LG2025

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

Yang Zhang, Rui Zhang, Jiaming Guo +10

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design.…

cs.LG2025

RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs

Pengwei Jin, Di Huang, Chongxiao Li +10

The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evalua…