Max's picture

5 3

Max

ZhMax

·

AI & ML interests

None yet

Organizations

None yet

upvoted a paper 2 months ago

ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression

Paper • 2602.11008 • Published Feb 11 • 18

upvoted an article 6 months ago

Article

Smol2Operator: Post-Training GUI Agents for Computer Use

+3

Sep 23, 2025

•

138

upvoted a paper 11 months ago

Risk-Averse Reinforcement Learning with Itakura-Saito Loss

Paper • 2505.16925 • Published May 22, 2025 • 26

upvoted a paper over 1 year ago

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

Paper • 2408.15300 • Published Aug 27, 2024 • 3

upvoted an article almost 2 years ago

Article

Fine-tune Llama 3 with ORPO

Apr 22, 2024

•

240