Baihui Liu

According to our database, Baihui Liu authored at least 7 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

A survey on memory-efficient transformer-based model training in AI for science.

Kaiyuan Tian, Linbo Qiao, Baihui Liu, Gongqingjian Jiang, Shanshan Li, Dongsheng Li

Frontiers Comput. Sci., November, 2026

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference.

Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li

CoRR, April, 2026

GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning.

Kaiyuan Tian, Yu Tang, Gongqingjian Jiang, Baihui Liu, Yifu Gao, Xialin Su, Linbo Qiao, Dongsheng Li

CoRR, April, 2026

ParaDySe: A Parallel Strategy Switching Framework for Dynamic Sequences in Transformer-based Large Language Models.

Zhixin Ou, Peng Liang, Linbo Qiao, Jianchen Han, Baihui Liu

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs.

Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li

CoRR, December, 2025

ParaDySe: A Parallel-Strategy Switching Framework for Dynamic Sequence Lengths in Transformer.

Zhixin Ou, Peng Liang, Jianchen Han, Baihui Liu, Linbo Qiao

CoRR, November, 2025

A Survey on Memory-Efficient Large-Scale Model Training in AI for Science.

Kaiyuan Tian, Linbo Qiao, Baihui Liu, Gongqingjian Jiang, Dongsheng Li

CoRR, January, 2025