Get started
Author

Kaiyuan Tian

Observed name: Tian, Kaiyuan
OpenAlex ID: A5133364630
A survey on memory-efficient transformer-based model training in AI for science
2026 · Kaiyuan Tian, Linbo Qiao, et al. · Frontiers of Computer Science · 3
PDF
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
2026 · Association for Computational Linguistics 2026, Li, Dongsheng, et al. · Underline Science Inc.
GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning
2026 · Tian, Kaiyuan, Tang, Yu, et al. · arXiv (Cornell University)
PDF
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
2026 · Liu, Baihui, Tian, Kaiyuan, et al. · arXiv (Cornell University)
PDF
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
2026 · Baihui Liu, Kaiyuan Tian, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning
2026 · Kaiyuan Tian, Linbo Qiao, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Works count: 6
Citation count: 3
H-index: 1
I10-index:
Year
Topic
Type