collaborators

5 papers

cs.AR2026

TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving

Chenxu Niu

Energy-aware LLM serving requires comparing configurations under realistic request shapes, yet exhaustive target-GPU profiling is costly and a cheap predictor can be dangerously co…

cs.AI2026

MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration

Jia Xiong, Runkai Li, Chenxu Niu +11

Microarchitecture design space exploration suffers from expansive search spaces and expensive PPA evaluation, leaving only a small simulation budget for design decision-making. Exi…

cs.LG2026

CiteRadar: A Citation Intelligence Platform for Researcher Profiling and Geographic Visualization

Chenxu Niu, Yiming Sun

Understanding the geographic reach and community structure of one's scholarly citations is increasingly valuable for career development, grant applications, and collaboration disco…

cs.ET2026

RTLocating: Intent-aware RTL Localization for Hardware Design Iteration

Changwen Xing, Yanfeng Lu, Lei Qi +5

Industrial chip development is inherently iterative, favoring localized, intent-driven updates over rewriting RTL from scratch. Yet most LLM-Aided Hardware Design (LAD) work focuse…

cs.LG2025

TokenPowerBench: Benchmarking the Power Consumption of LLM Inference

Chenxu Niu, Wei Zhang, Jie Li +4

Large language model (LLM) services now answer billions of queries per day, and industry reports show that inference, not training, accounts for more than 90% of total power consum…