7 papers
SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration
Renye Yan, Jikang Cheng, You Wu +5
Diffusion models have general generative abilities but struggle to align with specific objectives. Fine-tuning can improve alignment, yet its training cost is often prohibitive. Th…
Pixel-Space Diffusion Transformers
Renye Yan, Jikang Cheng, You Wu +8
Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine tex…
PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model
Renye Yan, Jikang Cheng, You Wu +4
While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement…
Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models
Renye Yan, Jikang Cheng, You Wu +4
Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult…
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
Renye Yan, Jikang Cheng, Shikun Sun +7
Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignment through explicit rewards.…
AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning
Renye Yan, Yaozhong Gan, You Wu +4
In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. H…
The Exploration-Exploitation Dilemma Revisited: An Entropy Perspective
Renye Yan, Yaozhong Gan, You Wu +4
The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces lea…