5 papers
Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrödinger Bridge
Yuehu Gong, Zeyuan Wang, Yulin Chen +3
Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically ins…
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Zeyuan Wang, Da Li, Yulin Chen +6
Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but str…
iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models
Xuezhi Cui, Dongbo Zhou, Wang Guo +8
Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning iso…
One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
Zeyuan Wang, Da Li, Yulin Chen +4
We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with…
FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection
Yulin Chen, Zeyuan Wang, Tianyuan Yu +2
The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based met…