Enshu Liu

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs