5 papers
Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
Ke Jiang, Wen Jiang, Yoshinobu Kawahara +1
We aim to address the problem of Out-of-Distribution (OOD) Mode Averaging, a critical problem that emerges when distilling Flow Matching (FM) based behavior policies in offline Rei…
Contrastive Desensitization Learning for Cross Domain Face Forgery Detection
Lingyu Qiu, Ke Jiang, Xiaoyang Tan
In this paper, we propose a new cross-domain face forgery detection method that is insensitive to different and possibly unseen forgery methods while ensuring an acceptable low fal…
RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment
Lingyu Qiu, Ke Jiang, Xiaoyang Tan
Recent advancements in domain generalization for deepfake detection have attracted significant attention, with previous methods often incorporating additional modules to prevent ov…
Variational OOD State Correction for Offline Reinforcement Learning
Ke Jiang, Wen Jiang, Xiaoyang Tan
The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular…
Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning
Ke Jiang, Wen Jiang, Yao Li +1
We address the challenge of offline reinforcement learning using realistic data, specifically non-expert data collected through sub-optimal behavior policies. Under such circumstan…