7 papers
AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
Dailan He, Guanlin Feng, Xingtong Ge +5
Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement lear…
Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models
Dailan He, Guanlin Feng, Xingtong Ge +6
Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching model…
High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning
Dailan He, Xiahong Wang, Shulun Wang +5
Face swapping aims to seamlessly transfer a source facial identity onto a target while preserving target attributes such as pose and expression. Diffusion models, known for their s…
SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction
Yang Zhou, Hao Shao, Letian Wang +3
Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of…
UniZero: Generalized and Efficient Planning with Scalable Latent World Models
Yuan Pu, Yazhe Niu, Zhenjie Yang +3
Learning predictive world models is crucial for enhancing the planning capabilities of reinforcement learning (RL) agents. Recently, MuZero-style algorithms, leveraging the value e…
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
Hao Shao, Shulun Wang, Yang Zhou +7
Video face swapping is becoming increasingly popular across various applications, yet existing methods primarily focus on static images and struggle with video face swapping becaus…