🔄 In a Training Loop

dong zi

shenyao

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing

upvoted a paper 2 days ago

Towards Flash Thinking via Decoupled Advantage Policy Optimization

upvoted a paper 2 days ago

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective

View all activity

Organizations

liked a Space over 2 years ago

Open LLM Leaderboard

Track, rank and evaluate open LLMs and chatbots

liked a dataset almost 3 years ago

m-a-p/COIG-CQIA

Viewer • Updated Apr 18, 2024 • 44.7k • 13.3k • 794

liked a dataset over 3 years ago

ecnu-icalk/educhat-sft-002-data-osm

Viewer • Updated Jul 1, 2023 • 4.28M • 357 • 38