arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Jinbao Xue"" — arXiv2 Search
Showing 1–3 of 3 results
/ Date
/ Name
May 21, 2025
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Dec 10, 2024
Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment
Jul 16, 2024
MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training