PhD candidate, The University of Melbourne
-
The University of Melbourne
- Melbourne, AU
-
04:58
(UTC +11:00)
Stars
5
results
for source starred repositories
Clear filter
[NAACL 2025 Main] Official Implementation of MLLMU-Bench
[NeurIPS D&B '25] The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning methods with easily feature extensibility.
[ICML 2024] "Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training"
[ICML 2024] Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models