← authors · overview

• Dual Attention Network For Scene Segmentation
  2018 · 6823 citations
• Adaptive Context Network For Scene Parsing
  2019 · 156 citations
• Dense Text Retrieval Based On Pretrained Language Models: A Survey
  2022 · 152 citations
• Scalable Vision Transformers With Hierarchical Pooling
  2021 · 129 citations
• Minicache: KV Cache Compression In Depth Dimension For Large Language Models
  2024 · 96 citations
• QLLM: Accurate And Efficient Low-bitwidth Quantization For Large Language Models
  2023 · 75 citations
• Cm-masksd: Cross-modality Masked Self-distillation For Referring Image Segmentation
  2023 · 19 citations
• Ecoformer: Energy-saving Attention With Linear Complexity
  2022 · 16 citations
• Vquala 2025 Challenge On Visual Quality Comparison For Large Multimodal Models: Methods And Results
  2025 · 7 citations
• Align Is Not Enough: Multimodal Universal Jailbreak Attack Against Multimodal Large Language Models
  2025 · 5 citations