Xuefeng Xiao

4 papers South China University of Technology

• Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
• LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
• PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
• VarFlow: Proper Scoring-Rule Diffusion Distillation via Energy Matching