Electrocatalytic nitrite reduction coupled with plasma nitrogen oxidation offers a promising route for ambient ammonia synthesis, yet simultaneously achieving high activity and stability remains challenging owing to high kinetic barriers and catalyst deactivation. Here, we develop a robust hybrid electrocatalyst for...
Zeroth-order (ZO) optimization with SGD in random subspaces enables memory-efficient fine-tuning of large language models without backpropagation. However, high gradient estimation noise fundamentally undermines adaptive optimizers like Adam. We propose SubZero+, which achieves practical adaptive ZO optimization throug...
Zi-Ming Yu, Shu-Yao Xiao, Xingyu Zhao et al.· 0 citations
FromPitch2Board, a deterministic football-management benchmark that studies five configurable factors through controlled comparisons on a single simulator, is introduced, showing that responsibility scope and horizon expose behavior changes that a single headline score conceals.
FlashPDE provides a hardware-efficient execution layer that bridges differentiable PDE solvers and GPU-optimized numerical computation within the PyTorch ecosystem, while maintaining numerical agreement with PyTorch finite-difference references.
KernelGenBench is presented, the first unified multi-source and multi-chip infrastructure for evaluating LLM- and agent-generated Triton kernels and establishes operator source, hardware platform, and agentic scaffold as distinct dimensions of kernel-generation capability, and shows that success in a familiar source-ha...
Pei-Yu Zang, Jian-Hang Tao, Jia-Ling Zhang et al.· 0 citations
It is shown that agent-based methods consistently outperform pure LLM sampling methods, while cuBLAS operators are the most challenging across all methods, and a unified benchmark for systematically evaluating LLM-and agent-generated Triton kernels across diverse operator sources and heterogeneous hardware platforms is...
Experiments show that SubZero+, an improved SubZero framework that improves stability in three complementary ways, consistently outperforms prior ZO baselines, enlarges the stable learning-rate range, and narrows the gap to first-order methods with minimal extra memory overhead.
Ziming Yu, Shu-Yao Xiao, Xingyu Zhao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
