ACL Findings2025
DeepRTL2: A Versatile Model for RTL-Related Tasks
Yi Liu, Hongji Zhang, Yunhao Zhou, Zhengyuan Shi, Changran Xu, Qiang Xu
Abstract
The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding. While previous studies have demonstrated the efficacy of finetuning LLMs for these generation-based tasks, embedding-based tasks, which are equally critical to EDA workflows, have been largely overlooked. These tasks, including natural language code search, RTL code functionality equivalence checking, and performance prediction, are essential for accelerating and optimizing the hardware design process. To address this gap, we present DeepRTL2, a family of versatile LLMs that unifies both generation-and embedding-based tasks related to RTL. By simultaneously tackling a broad range of tasks, DeepRTL2 represents the first model to provide a comprehensive solution to the diverse challenges in EDA. Through extensive experiments, we show that DeepRTL2 achieves state-of-theart performance across all evaluated tasks.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models cites Language Models are Few-Shot Learners
- Topology Matters in RTL Circuit Representation Learning cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Topology Matters in RTL Circuit Representation Learning cites Learning Semantic Representations to Verify Hardware Designs
- UniRTL: Unifying Code and Graph for Robust RTL Representation Learning cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- UniRTL: Unifying Code and Graph for Robust RTL Representation Learning cites Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph Learning
Cited by top-tier papers4
- Beyond Tokens: Enhancing RTL Quality Estimation via Structural Graph LearningYi Liu, Hongji Zhang, Yiwen Wang, Dimitrios Tsaras et al.ICML 2026 · 1 citation
- QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog GenerationHanqi Lyu, Di Huang, Yaoyu Zhu, Kangcheng Liu et al.ICML 2026 · 1 citation
- Topology Matters in RTL Circuit Representation LearningMingyu Zhao, Xun He, Jiawei Liu, Jianwang Zhai et al.ICLR 2026
- UniRTL: Unifying Code and Graph for Robust RTL Representation LearningYi Liu, Hongji Zhang, Lei Chen, Mingxuan Yuan et al.ICML 2026
Builds on9
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Scaling Sentence Embeddings with Large Language ModelsTing Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang et al.EMNLP Findings 2024 · 61 citations
- Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation frameworkKaiyan Chang, Kun Wang, Nan Yang, Ying Wang et al.DAC 2024 · 59 citations
- Learning Semantic Representations to Verify Hardware DesignsShobha Vasudevan, Wenjie Jiang, David Bieber, Rishabh Singh et al.NeurIPS 2021 · 38 citations
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding ModelsChankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman et al.ICLR 2025
Related papers
- DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation ModelYi Liu, Changran Xu, Yunhao Zhou, Zeju Li et al.ICLR 2025
- Hardware Generation with High Flexibility using Reinforcement Learning Enhanced LLMsYifang Zhao, Weimin Fu, Shijie Li, Yi-Xiang Hu et al.DAC 2025 · 1 citation
- UVLLM: An Automated Universal RTL Verification Framework using LLMsYuchen Hu, Junhao Ye, Ke Xu, Jialin Sun et al.DAC 2025 · 4 citations
- QiMeng-CodeV-R1: Reasoning-Enhanced Verilog GenerationYaoyu Zhu, Di Huang, Han-Qi Lyu, Xiaoyun Zhang et al.NeurIPS 2025 · 46 citations
- EmbedAgent: Benchmarking Large Language Models in Embedded System DevelopmentRuiyang Xu, Jialun Cao, Mingyuan Wu, Wenliang Zhong et al.ICSE 2026
