Xiang Shi's picture

In a Training Loop 🔄

Xiang Shi

KevinZonda

·

https://kevinzonda.com

AI & ML interests

Natural Language Processing, Computer Vision & Machine Learning for Medical Imaging

Recent Activity

upvoted a paper 12 days ago

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

liked a model 20 days ago

facebook/sam3.1

liked a model 20 days ago

mlx-community/sam3.1-bf16

View all activity

Organizations

upvoted a paper 12 days ago

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation

Paper • 2604.23750 • Published 28 days ago • 1

upvoted 2 collections 9 months ago

MedSPO

MedSPO is a model family which fine-tuned Qwen2.5-Instruct models specifically designed for biomedical subject-predicate-object (SPO) extraction tasks • 4 items • Updated Sep 4, 2025 • 2

Qwen3

84 items • Updated Dec 31, 2025 • 1.79k