Yize Cheng

yizecheng

·

https://chengez.github.io

chengez

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions

authored a paper 1 day ago

When is Your LLM Steerable?

authored a paper 1 day ago

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

View all activity

Organizations

Papers 10

arxiv:2608.07968

arxiv:2606.11599

arxiv:2605.14038

arxiv:2601.22345

models 0

None public yet

datasets 2

yizecheng/model-adaptive-tool-necessity

Viewer • Updated May 26 • 38.5k • 63

yizecheng/TicToc

Viewer • Updated Feb 6 • 5.59k • 53