arxiv:2609.33586
Shangzhen Zhu
ArgonnSZ
ยท
AI & ML interests
None yet
Recent Activity
submitted a paper 2 days ago
Pretraining Transformers with Quantized Softmax in Attention upvoted a paper 2 days ago
Softmax Reparameterization for Output-Head Quantization upvoted a paper 3 days ago
Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel AccelerationOrganizations
