CHORUS framework boosts hardware verification stimulus generation by 13.5% · arXiv

Researchers have developed CHORUS, a novel post-training framework for generating high-coverage testbench stimuli for hardware verification. By leveraging complementary strengths from staged SFT checkpoints and dense-reward RL, CHORUS consolidates specialists into a single 4B model. This approach significantly outperforms existing methods, achieving 88.0% Pass@1 on the CVDP-ECov benchmark, a 13.5 percentage point improvement over the much larger 671B DeepSeek-R1 model. AI

RANK_REASON The cluster describes a new research paper detailing a novel framework for stimulus generation in hardware verification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• CVDP-ECov
• DeepSeek-R1
• Hugging Face
• large-language models

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →