news

Nov 10, 2026 New preprint: AutoScaffold, an AI-for-AI framework that turns a student model’s RL training experience into adaptive scaffolds.
Jul 01, 2026 New preprint: Is One Layer Enough? Training a single transformer layer can match full-parameter RL training.
May 08, 2026 New preprint: CUDAHercules, a benchmark for hardware-aware, expert-level CUDA optimization with LLMs.
Apr 30, 2026 StitchCUDA is accepted to ICML 2026.
Jan 31, 2026 GRAPE is accepted to ICRA 2026.
Oct 23, 2025 New preprint: CudaForge, a multi-agent workflow with hardware feedback for CUDA kernel optimization.
Sep 18, 2025 InfantAgent-Next is accepted to NeurIPS 2025.
Sep 02, 2025 Started my PhD in Electrical and Computer Engineering at the University of Minnesota, advised by Prof. Mingyi Hong.