Wensong Bai — accepted AI-conference papers

2025

Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning

Wensong Bai, Chufan Chen, Yichao Fu, Qihang Xu, Chao Zhang, Hui Qian

NeurIPS 2025poster

Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of conditional sequence modeling (CSM), a paradigm that models the action distribution conditioned on both historical trajectories and target returns associated with each state. However, due to the imbalance…

Cited by 0 Source ↗Scholar ↗

2023

Towards Optimal Randomized Strategies in Adversarial Example Game

Jiahao Xie, Chao Zhang, Weijie Liu, Wensong Bai, Hui Qian

AAAI 2023technical

The vulnerability of deep neural network models to adversarial example attacks is a practical challenge in many artificial intelligence applications. A recent line of work shows that the use of randomization in adversarial training is the key to find optimal strategies against adversarial example at…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗