Xuefeng Xiao

Flow Caching for Autoregressive Video Generation

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Quantization Meets Sparsification for Faster Image Generation

Reinforcement Reward Model with Policy Feedback

SplitQuant: Efficient Low-Bit Quantization for Diffusion Transformers via In-Channel Dimension Splitting

LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process

VarFlow: Proper Scoring-Rule Diffusion Distillation via Energy Matching

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

polybasic Speculative Decoding Through a Theoretical Perspective

Diffusion Adversarial Post-Training for One-Step Video Generation

Polybasic Speculative Decoding Under a Theoretical Perspective