Yinggan Xu's picture

3 6 7

Yinggan Xu

Dibbla

·

https://dibbla.space/

AI & ML interests

LLM for Science, Human-centered AI and Robot Learning

Recent Activity

authored a paper 1 day ago

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

upvoted a paper 2 days ago

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

submitted a paper 2 days ago

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

View all activity

Organizations

upvoted 2 papers 2 days ago

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost

Paper • 2602.03120 • Published 15 days ago • 1

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning

Paper • 2509.24372 • Published Sep 29, 2025 • 11

upvoted a collection 6 months ago

Hermes 4 Collection

13 items • Updated Dec 2, 2025 • 81

upvoted an article 9 months ago

Article

Introduction to 3D Gaussian Splatting

Sep 18, 2023

•

128

upvoted a paper 9 months ago

Advancing AI-Scientist Understanding: Making LLM Think Like a Physicist with Interpretable Reasoning

Paper • 2504.01911 • Published Apr 2, 2025 • 1

upvoted an article over 1 year ago

Article

The Annotated Diffusion Model

Jun 7, 2022

•

321