Ziyang Miao's picture

1 5 7

Ziyang Miao

hvgg1ngface

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

upvoted a paper about 1 month ago

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

upvoted a paper about 2 months ago

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents

View all activity

Organizations

None yet

upvoted 2 papers about 1 month ago

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Paper • 2507.17512 • Published Jul 23 • 36

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published Jul 15 • 63

upvoted a paper about 2 months ago

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents

Paper • 2507.04009 • Published Jul 5 • 41

upvoted a paper 11 months ago

DoRA: Weight-Decomposed Low-Rank Adaptation

Paper • 2402.09353 • Published Feb 14, 2024 • 28

upvoted an article 12 months ago

Article

Generating Human-level Text with Contrastive Search in Transformers 🤗

Nov 8, 2022

• 17