← authors · overview

• CMT: Convolutional Neural Networks Meet Vision Transformers
  2021 · 749 citations
• Distilling Object Detectors Via Decoupled Features
  2021 · 217 citations
• Hit-detector: Hierarchical Trinity Architecture Search For Object Detection
  2020 · 77 citations
• Hire-mlp: Vision MLP Via Hierarchical Rearrangement
  2021 · 62 citations
• Discernible Image Compression
  2020 · 25 citations
• Veattack: Downstream-agnostic Vision Encoder Attack Against Large Vision Language Models
  2025
• Circle-rope: Cone-like Decoupled Rotary Positional Embedding For Large Vision-language Models
  2025
• Consistency-driven Calibration And Matching For Few-shot Class-incremental Learning
  2025
• SRSR: Enhancing Semantic Accuracy In Real-world Image Super-resolution With Spatially Re-focused Text-conditioning
  2025
• Enhancing Physical Plausibility In Video Generation By Reasoning The Implausibility
  2025