Get started
Author

Tao Lan

Observed name: Lan, Tao
Observed institution: Alibaba Group (China)
ORCID: 0009-0004-4363-8888
Observed ORCID: 0009-0004-4363-8888
OpenAlex ID: A5133359474
C 2 KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
2026 · Chuheng Du, Junyi Chen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 6
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
2026 · Zhou, Yanke, Li, Yiduo, et al. · arXiv (Cornell University) · 5
PDF
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
2026 · Li, Maohua, Li, Qirui, et al. · arXiv (Cornell University) · 4
PDF
RTP-LLM: High-Performance Alibaba LLM Inference Engine
2026 · Tan, Boyu, Guo, Jiarui, et al. · arXiv (Cornell University) · 4
PDF
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
2026 · Li, Kesong, Xu, Yixuan, et al. · arXiv (Cornell University) · 4
PDF
Rethinking Cross-Layer Information Routing in Diffusion Transformers
2026 · Xu, Chao, Li, Maohua, et al. · arXiv (Cornell University) · 3
PDF
FlashPS: Efficient Generative Image Editing with Mask-aware Caching and Scheduling
2026 · Xiaoxiao Jiang, Suyi Li, et al. · European Conference on Computer Systems · 1
D i F low : A System for Micro-Serving Text-to-image Di ffusion Work flows
2026 · Lingyun Yang, Suyi Li, et al. · ACM SIGOPS Symposium on Operating Systems Principles (SOSP)
PDF
RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
2026 · Cong, Xing, Tang, Hanlin, et al. · arXiv (Cornell University)
PDF
Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
2026 · Guo, Jiarui, Xu, Yuemeng, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 27
H-index: 4
I10-index:
Year
Topic
Type