Lune

Profiles2023-2026

Yuqing Yang

Microsoft Research

15Papers
4Last author
46Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers15

  1. Region-Adaptive Sampling for Diffusion TransformersAuthor 7 of 7CVPR 2026 · 35 citations
  2. From Struggle to Success: Context-Aware Guidance for Screen Reader Users in Computer UseAuthor 6 of 6CHI 2026 · 1 citation
  3. RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM InferenceAuthor 17 of 20VLDB 2026 · 1 citation
  4. RetrievalAttention: Accelerating Long-Context LLM Inference via Vector RetrievalAuthor 13 of 14NeurIPS 2025 · 148 citations
  5. Mitigate Position Bias in LLMs via Scaling a Single Hidden States ChannelAuthor 7 of 9ACL Findings 2025 · 5 citations
  6. LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt CompressionAuthor 6 of 7ACL 2024 · 59 citations
  7. LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt CompressionAuthor 9 of 13ACL Findings 2024 · 58 citations
  8. VisEval: A Benchmark for Data Visualization in the Era of Large Language ModelsAuthor 5 of 5IEEE VIS 2024 · 44 citations
  9. Position Engineering: Boosting Large Language Models through Positional Information ManipulationAuthor 4 of 6EMNLP 2024 · 3 citations
  10. Benchmarking Data Science AgentsAuthor 5 of 7ACL 2024
  11. LLMLingua: Compressing Prompts for Accelerated Inference of Large Language ModelsAuthor 4 of 5EMNLP 2023 · 94 citations
  12. ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image ManipulationAuthor 5 of 9NeurIPS 2023 · 71 citations
  13. Attentive Mask CLIPAuthor 11 of 11ICCV 2023 · 37 citations
  14. Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceAuthor 8 of 24KDD 2023 · 12 citations
  15. EfficientViT: Memory Efficient Vision Transformer with Cascaded Group AttentionAuthor 4 of 6CVPR 2023
Dusk over the sea between two cliffs drawn in fine vertical lines