7 papers
Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion
Henglin Liu, Fangyuan Kong, Jing Wang +7
The paper introduces concentrated Implicit Preference Optimization (cIPO), a post‑training method for text‑to‑video diffusion models that derives preference signals from reconstruc…
Embedding-perturbed Exploration Preference Optimization for Flow Models
Sujie Hu, Chubin Chen, Jiashu Zhu +3
Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-based optimization framework…
MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer
Nisha Huang, Henglin Liu, Yizhou Lin +5
Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extr…
KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration
Ruicheng Zhang, Kaixi Cong, Jun Zhou +5
Aligning streaming autoregressive (AR) video generators with human preferences is challenging. Existing reinforcement learning methods predominantly rely on noise-based exploration…
Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning
Chubin Chen, Sujie Hu, Jiashu Zhu +8
Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, whil…
Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
Chubin Chen, Jiashu Zhu, Xiaokun Feng +7
Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for enhancing sample quality and prompt adherence. However, through an empirical analysis on Ga…