Gausson Tschen's picture

Gausson Tschen

Gausson

·

https://www.xiaohongshu.com/user/profile/615bd9080000000002018213

AI & ML interests

LLM Architecture, Pre-training, Deep Neural Network Optimization, Sparsity

Recent Activity

upvoted a paper about 23 hours ago

UniPool: A Globally Shared Expert Pool for Mixture-of-Experts

new activity 9 months ago

nvidia/kvpress-leaderboard:Upload the results of the training-free version of the method [SepLLM - ICML 2025 Paper](https://arxiv.org/abs/2412.12094) based on "meta-llama/Meta-Llama-3.1-8B-Instruct"

updated a model 9 months ago

Gausson/sep_cache

View all activity

Organizations

Gausson 's datasets

None public yet