← authors · overview

• Swiftnet: Real-time Video Object Segmentation
  2021 · 165 citations
• Occluded Video Instance Segmentation: A Benchmark
  2021 · 133 citations
• Pyramidinfer: Pyramid KV Cache Compression For High-throughput LLM Inference
  2024 · 130 citations
• VISA: Reasoning Video Object Segmentation Via Large Language Models
  2024 · 34 citations
• Salient Object Ranking With Position-preserved Attention
  2021 · 22 citations
• From Image To Video, What Do We Need In Multimodal Llms?
  2024 · 16 citations
• Scalable Overload-aware Graph-based Index Construction For 10-billion-scale Vector Similarity Search
  2025 · 3 citations