Jun Gao
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
SecureAFL introduces a robust framework to secure asynchronous Federated Learning against poisoning attacks by detecting anomalous updates, estimating missing client contributions, and using Byzantine-robust aggregation.
The paper introduces VikingMem, a novel Memory Base Management System that effectively manages the persistent state of long-term LLM interactions by selectively extracting, evolving, and compressing memories, significantly outperforming existing methods.
The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto large shared foundation models.
The paper introduces a Mixture-Density Representation (MDA) to model depth ambiguity, effectively eliminating 'flying-point' artifacts at object boundaries by allowing pixels to predict multiple possible depths.
The paper introduces AFUN, a model that predicts both the location (functional mask) and the motion (3D curve) for robot interaction, aiming to create a generalizable foundation model for understanding object functionality.
Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.
Papers
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Anjun Gao, Yueyang Quan, Yufei Xia, Zhuqing Liu +1 more
Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.