2 papers
cond-mat.mtrl-sci2026
MOFFieldBench: A Machine Learning Benchmark for Continuous Electronic Fields in Metal-Organic Frameworks
Zhaolin Hu, Hehe Fan, Chenhao Rao +4
Machine-learning models for metal-organic frameworks (MOFs) predominantly rely on atomic structures, whereas electron-density (ED) and electrostatic-potential (ESP) fields remain u…
cs.AR2026
HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators
Zhixiang Wei, Yun Wang, James Yen +2
LLM inference comprises a compute-bound prefill phase and a memory-bound decode phase, and recent systems disaggregate them onto separate hardware. Yet today's datacenter GPUs rely…