PPaperPicks

Zhijun Tu

8 papers at tracked venues · 7 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution
  2. AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution
  3. CBQ: Cross-Block Quantization for Large Language Models
  4. Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts
  5. Effective Diffusion Transformer Architecture for Image Super-Resolution
  6. RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler
  7. PQ-SAM: Post-training Quantization for Segment Anything Model
  8. U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers