arxiv:2505.15431
han weidong
dongdong2021
AI & ML interests
NLP;Multi-modal;LLM
Recent Activity
upvoted a paper about 13 hours ago
TransMamba: Flexibly Switching between Transformer and Mamba authored
a paper
5 months ago
Lossless KV Cache Compression to 2% authored
a paper
5 months ago
Hunyuan-TurboS: Advancing Large Language Models through
Mamba-Transformer Synergy and Adaptive Chain-of-Thought