Anyi Xu
Anyi Xu has 2 papers in our library, in 2026, most of them on Efficient models & compression; often with Bangcai Lin, Bing Xue, Bingzheng Xu.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 121 times in our library · ⭐ Paper Stars ranking: #6492
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 1Research subjects and languages the work is about.Efficient models & compression · 2 works
Works by year
2020s
Papers
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence (2026 · 122 citations)
Reasoning LLMs improve when they spend more compute at inference time. Standard attention, however, grows quadratically with sequence length, which makes very long inputs and extended agentic workflows costly. DeepSeek-V4 is a preview family of two MoE models, DeepSeek-V4-Pro and DeepSeek-V4-Flash, built to process… - DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression (2026 · 3 citations)
Long-running AI agents mostly consume input tokens. As a result, serving cost now depends less on attention compute and more on the size of key-value (KV) caches. These caches must fit in HBM, be kept on SSD or host memory for prefix reuse, and be moved over limited bandwidth. DeepSeek-AI presents…
Co-authors here
- Bangcai Lin ×2
- Bing Xue ×2
- Bingzheng Xu ×2
- Bochao Wu ×2
- Bowei Zhang ×2
- DeepSeek-AI ×2
- Bingxuan Wang
- Boyi Deng
- Chaofan Lin
- Chen Dong
- Chengda Lu
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/anyi-xu/