Ying Wen

LLMs can now synthesize high-performance kernels for niche hardware like NPUs, even with limited data, thanks to a self-evolving agent that bootstraps and refines code via value-driven reinforcement learning.

MLLMs can slash 68% of their FLOPs with minimal accuracy loss by pruning visual tokens at the "Entropy Collapse Layer"—where information content plummets—using a new matrix-entropy-guided method.

Function calling gets a serious upgrade: a new reward model and inference scaling technique boosts performance by focusing on the *process* of tool use, not just the outcome.