Carole-Jean Wu

How Text Quality Interventions Reshape Neural Scaling Laws for LLMs: Empirical Study

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead

Composer: A Search Framework for Hybrid Neural Architecture Design

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench