logo
today local_bar

Hao Zhu

Postdoc, CSIRO

2 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Machine Unlearning via Task Simplex Arithmetic
#1510 · Junhao Dong, Hao Zhu, Yifei Zhang, Xinghua Qu, Yew-Soon Ong, Piotr Koniusz

VLM unlearning by a closed-form ensemble of infinite number of functions with parameters uniformly sampled from a task arithmetic simplex.

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
#2613 · Yifei Zhang, Hao Zhu, Junhao Dong, Haoran Shi, Ziqiao Meng, Piotr Koniusz, Han Yu

How to employ the coherence between layers to design a PEFT method.