Fan Wu

Toward Understanding the Influence of Individual Clients in Federated Learning

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guarantee of the global model, however, it is still …

SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination

2022 · arXiv (Cornell University)

Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises extensive concerns on …

Secure and Efficient Blockchain based Knowledge Sharing for Intelligent Connected Vehicles

2021 · arXiv (Cornell University)

The emergence of Intelligent Connected Vehicles (ICVs) shows great potential for future intelligent traffic systems, enhancing both traffic safety and road efficiency. However, the ICVs relying on data driven perception and driving models face many …

Privately Aligning Language Models with Reinforcement Learning

2023 · arXiv (Cornell University)

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we initiate the study …

Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation

2025

In cloud-centric recommender system, regular data exchanges between user devices and cloud could potentially elevate bandwidth demands and privacy risks. On-device recommendation emerges as a viable solution by performing reranking locally to alleviate these concerns. …

Estimated Informed Anytime Search for Sampling-Based Planning via Adaptive Sampler

2025 · IEEE Transactions on Automation Science and Engineering

Path planning in robotics often involves solving continuously valued, high-dimensional problems. Popular informed approaches include graph-based searches, such as A*, and sampling-based methods, such as Informed RRT*, which utilize informed set and anytime strategies to …

TSRec: Enhancing Repeat-Aware Recommendation from a Temporal-Sequential Perspective

2025 · arXiv (Cornell University)

Repeat consumption, such as repurchasing items and relistening songs, is a common scenario in daily life. To model repeat consumption, the repeat-aware recommendation has been proposed to predict which item will be re-interacted based on …