Hai-Zhao Yang

Frontier LLM agents fail to recognize superior human-corrected scientific research plans, performing worse than chance even with full project context.

A sharp width--magnitude tradeoff at fixed depth is established using one elementary bounded $1$-Lipschitz Dyadic--Triangular Activation and yields a continuum of statistically optimal choices, ranging from unit parameter radius to fixed network size.

AutoSR not only recovers complex equations but also retains the entire scientific rationale behind them, revolutionizing how we approach symbolic regression.

Achieving an unprecedented reduction in storage costs for high-dimensional function optimization, this method allows for efficient training of deep neural networks in dimensions previously deemed impractical.

Sparsification in attention mechanisms can drastically alter content influence, with higher compression ratios leading to surprising shifts in model output that standard accuracy metrics overlook.

Renormalization can redefine how we understand and address the sim-to-real gap in robotics by leveraging effective parameters that capture omitted dynamics.

A neural scorer fine-tuned on NASA's Earth Observation data outperforms traditional methods, while a zero-shot reranking stage boosts retrieval effectiveness by 28%.