The MHA2MLA-VLM model published in the paper "MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models"
Xiaoran Fan
cnxup
AI & ML interests
NLP, CV, LLM
Recent Activity
upvoted a paper about 1 month ago
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining liked a dataset 7 months ago
sysuyy/ImgEdit liked a model 8 months ago
cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_128Organizations
None yet