Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jun Gao

Jun Gao

6 indexed papers

Recent (6 mo)
6
With code
0
Influential cites
0
Benchmarked
0

Publications per year

6
26

Top categories

AI×3ML×3Crypto×2Vision×2Info Retrieval×1NLP×1Robotics×1Distributed×1

Frequent co-authors

Anjun Gao2×
Yueyang Quan2×
Zhuqing Liu2×
Minghong Fang2×
Yufei Xia1×
Mind Lab1×

Research Timeline

2026
SecureAFL: Secure Asynchronous Federated Learning

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.

VikingMem: A Memory Base Management System for Stateful LLM-based Applications

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.

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

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.

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation

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.

AFUN: Towards an Affordance Foundation Model for Functionality Understanding

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: Post-Hoc Patching of Backdoored Large Language Models

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.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.IRRecentJun 2, 2026

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.

View →
cs.LGcs.CLRecentJun 1, 2026

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Mind Lab, :, Song Cao, Vic Cao +51 more

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 l…

View →
cs.CVcs.AIRecentJun 1, 2026

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation

Siyuan Bian, Congrong Xu, Jun Gao

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 possi…

View →
cs.ROcs.CVRecentJun 1, 2026

AFUN: Towards an Affordance Foundation Model for Functionality Understanding

Zhaoning Wang, Yi Zhong, Jiawei Fu, Henrik I. Christensen +1 more

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 understandin…

View →
cs.AIRecentMay 28, 2026

VikingMem: A Memory Base Management System for Stateful LLM-based Applications

Jiajie Fu, Junwen Chen, Mengzhao Wang, Aoxiang He +4 more

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 m…

View →
cs.CRcs.DCcs.LGRecentApr 4, 2026

SecureAFL: Secure Asynchronous Federated Learning

Anjun Gao, Feng Wang, Zhenglin Wan, Yueyang Quan +2 more

SecureAFL introduces a robust framework to secure asynchronous Federated Learning against poisoning attacks by detecting anomalous updates, estimating missing client contributions, and using Byzantine…

View →