Lu Chen

Lightweight LLMs can now generate high-quality data preparation pipelines for TableQA in a single step, outperforming multi-step approaches while slashing costs and latency.

GLM-5 doesn't just code; it engineers, showcasing unprecedented capability in tackling end-to-end software engineering challenges.

Forget painstakingly tuning force magnitudes for sim-to-real transfer of contact-rich tasks; this work shows that learning just the *direction* of contact forces unlocks surprisingly robust performance.