6 papers
FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management
Peiyu Zang
Long-horizon agent benchmarks typically report how far an agent progresses, but do not identify whether its performance comes from the foundation model, scaffold, responsibility sc…
Retracing Hodgkin and Huxley: State Recovery Does Not Certify Mechanism
Peiyu Zang, Jiayi Hao, Yongqiang Cai
Predicting observed dynamics does not establish recovery of the underlying physical mechanism. Can machine learning retrace the hidden-state reasoning behind the Hodgkin-Huxley (HH…
SubZero+: Memory-Efficient Adaptive Zeroth-Order LLM Fine-Tuning in Random Subspaces
Ziming Yu, Shuyao Xiao, Xingyu Zhao +6
Zeroth-order (ZO) optimization with SGD in random subspaces enables memory-efficient fine-tuning of large language models without backpropagation. However, high gradient estimation…
FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers
Peiyu Zang, Bosen Xie, Ruoxiang Xu +1
Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differenti…
KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?
Peiyu Zang, Jian Tao, Jialing Zhang +4
Modern AI systems depend on specialized accelerator kernels, whose development is complicated by increasingly diverse operators and hardware. LLMs and agentic systems promise to au…
Towards Automated Kernel Generation in the Era of LLMs
Yang Yu, Peiyu Zang, Chi Hsu Tsai +11
The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level ha…