Lattice AI Research

Research focus

Code Generation & Program Synthesis (2)Natural Language Processing (2)Open-Source Models & Weights (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Christoph Treude (3)Peerachai Banyongrakkul (2)Mansooreh Zahedi (2)Patanamon Thongtanunam (2)

Papers (3)

Apr 20, 2026

Peerachai Banyongrakkul +41w ago

When AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems

Pre-trained models in software projects aren't just libraries; they're sticky dependencies that accumulate over time and evolve based on capability, not just bug fixes.

Peerachai Banyongrakkul, Mansooreh Zahedi, Christoph Treude +2

Code Generation & Program Synthesis Natural Language Processing Open-Source Models & Weights

Apr 8, 2026

Hong Yi Lin +53w ago

Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision

LLMs are overconfident in automated code revision, but fine-grained calibration can cut their miscalibration error by leveraging local edit decisions.

Hong Yi Lin, Chunhua Liu, Haoyu Gao +3

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

Jan 20, 2026

Jan 20, 2026·also SMU

On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source

AI-generated code in open source gets a free pass: 80% of AI-co-authored pull requests from new contributors are merged without review, raising questions about code quality and security.

Haoyu Gao, Peerachai Banyongrakkul, Hao Guan +2

Search

Haoyu Gao

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (3)