Lattice AI Research

Research focus

Code Generation & Program Synthesis (2)Eval Frameworks & Benchmarks (2)Tool Use & Agents (1)Data Curation & Synthetic Data (1)

Frequent co-authors

Yitong Zhang (1)Chengze Li (1)Ruize Chen (1)Guowei Yang (1)

Papers (2)

Mar 16, 2026

Tsinghua AI1d ago·also Stanford HAI, Beihang, BIT, NJU +1

To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

LLMs struggle to effectively use private library APIs even when given the correct documentation, but PriCoder's data synthesis approach boosts performance by over 20%.

Yitong Zhang, Chengze Li, Ruize Chen +4

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Tool Use & Agents

Mar 15, 2026

2d ago

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

LLMs struggle with low-resource general-purpose programming languages, and surprisingly, translating code *to* a low-resource language is harder than generating it from text.

Junhang Cheng, Fang Liu, Jia Li +3

Code Generation & Program Synthesis Data Curation & Synthetic Data Eval Frameworks & Benchmarks

Search

Jia Li

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)