Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due to costly triplet supervision and complex task-dependent calibration. In contrast, text-to-image (T2I) generation benefits from a mature and diverse reward ecosystem spa...
Qi-Chao Ma, Ji-Kang Cheng, Ling Liang et al.· 1 citation
SwiftExplorer is proposed, a plugin that mitigates distribution collapse caused by excessive diversity loss and reduces compute costs, and adopts an Inheritance-Restart exploration mechanism to avoid early convergence, while exploration also increases the likelihood of high-reward trajectories.
Ren-Ye Yan, Ji-Kang Cheng, You Wu et al.· 0 citations
A Density-Aware Regional Decisive replay strategy, termed InfoDense, which effectively mitigates catastrophic forgetting while improving cross-domain generalization and knowledge retention and generalization.
Stage-Guided Per-Step Optimization (SGPO) is proposed for diffusion models, which jointly leverages signal-to-noise ratio and semantic changes to identify generation stages and adaptively assign stage-specific objectives.
Ren-Ye Yan, Ji-Kang Cheng, You Wu et al.· 1 citation
GenTrack is introduced, an online generator--tracker framework that alternates execution-grounded, group-relative generator alignment with tracker training on newly generated references; anchoring and rehearsal constrain drift and demonstrates that joint online post-training effectively narrows the executability gap be...
Zeyu Ling, Xinyao Yu, Renye Yan et al.· 0 citations
PAST is proposed, which provides differentiated rewards while adaptively regulating training episode length by jointly perceiving denoising progress and prompt difficulty and establishes a dual adaptive coordination mechanism that balances the extrinsic and intrinsic rewards.
Ren-Ye Yan, Ji-Kang Cheng, You Wu et al.· 0 citations
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 textures and structural details, while separate representation and diffusion training creates a mismatch between reconstruction and generation...
Ren-Ye Yan, Ji-Kang Cheng, You Wu et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
