Lattice AI Research

Research focus

Code Generation & Program Synthesis (3)Eval Frameworks & Benchmarks (2)Natural Language Processing (2)RLHF & Preference Learning (1)

Frequent co-authors

Zhiteng Chao (3)Yang Yin (2)Hongqin Lyu (2)Jiaxin Zhou (2)

Papers (3)

Apr 8, 2026

3w ago·also CAS, NJU, USTC

CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations

LLMs can now write better hardware verification code: CoverAssert boosts functional coverage by up to 15% by iteratively guiding LLMs with coverage feedback.

Yonghao Wang, Yang Yin, Hongqin Lyu +11

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Natural Language Processing

Mar 29, 2026

Mar 29, 2026·also PKU

RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning

Unlock better hardware designs: RTLSeek's diversity-oriented RL lets LLMs explore a wider range of Verilog implementations, boosting both correctness and design options.

Zhiteng Chao, Yonghao Wang, Bin Sun +5

Code Generation & Program Synthesis RLHF & Preference Learning

Feb 17, 2026

Iterative LLM-Based Assertion Generation Using Syntax-Semantic Representations for Functional Coverage-Guided Verification

LLMs can now generate significantly better SystemVerilog assertions by iteratively refining their outputs based on functional coverage feedback, boosting branch, statement, and toggle coverage by up to 15.69%.

Yonghao Wang, Jiaxin Zhou, Yang Yin +3

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Natural Language Processing

Search

Yonghao Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (3)