activity
20182025
most citedOn Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

23 citations · 29 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2025

Improving LLM Unlearning Robustness via Random Perturbations

Dang Huu-Tien, Hoang Thanh-Tung, Anh Bui +3

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the…

cs.CL2023

Class based Influence Functions for Error Detection

Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran +4

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we…