Yao Fu
5
Papers
306
Total Citations
1
Affiliations
Affiliations
University of Edinburgh
Papers (5)
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
ICLR 2025arXiv
165
citations
Retrieval Head Mechanistically Explains Long-Context Factuality
ICLR 2025arXiv
140
citations
RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis
NeurIPS 2025arXiv
1
citations
Data Engineering for Scaling Language Models to 128K Context
ICML 2024
0
citations
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
ICML 2024
0
citations