KABI's picture

KABI

dongguanting

·

https://dongguanting.github.io/

AI & ML interests

Reasoning and Alignment for Large Language Models

Recent Activity

upvoted a paper about 11 hours ago

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

commentedon a paper about 15 hours ago

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

upvoted a paper about 15 hours ago

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

View all activity

Organizations

commented a paper about 15 hours ago

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Paper • 2604.02029 • Published 2 days ago • 95 •

New activity in dongguanting/Tool-Star-Qwen-1.5B 29 days ago

Update README.md

#1 opened 3 months ago by

New activity in dongguanting/Qwen2.5-7B-AEPO 5 months ago

Update pipeline tag

#2 opened 5 months ago by

New activity in dongguanting/Qwen3-8B-AEPO-DeepSearch 5 months ago

Update pipeline tag

#2 opened 5 months ago by

New activity in dongguanting/Qwen3-14B-AEPO-DeepSearch 5 months ago

Improve model card for Qwen3-14B-AEPO-DeepSearch with pipeline tag, Transformers library, and GitHub link

#1 opened 6 months ago by

New activity in dongguanting/Qwen3-8B-AEPO-DeepSearch 5 months ago

Improve model card: Add pipeline tag, library name, abstract, and links

#1 opened 6 months ago by

New activity in dongguanting/Qwen2.5-7B-AEPO 5 months ago

Improve model card: Add metadata, abstract, and GitHub link for AEPO

#1 opened 6 months ago by

commented 2 papers 6 months ago

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16, 2025 • 107 •

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16, 2025 • 107 •

New activity in dongguanting/Qwen2.5-7B-ARPO 8 months ago

The model name error

#3 opened 8 months ago by

commented a paper 8 months ago

HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

Paper • 2508.08088 • Published Aug 11, 2025 • 29 •

New activity in dongguanting/ARPO-SFT-54K 8 months ago

Improve dataset card: Add metadata, detailed description, and usage

#2 opened 8 months ago by

New activity in dongguanting/Llama3.1-8B-ARPO 8 months ago

Enhance model card with metadata and details

#1 opened 8 months ago by

New activity in dongguanting/Qwen2.5-3B-ARPO 8 months ago

Enhance model card with metadata, abstract, usage, and comprehensive links

#1 opened 8 months ago by

New activity in dongguanting/Qwen3-14B-ARPO-DeepSearch 8 months ago

Enhance model card with metadata, abstract, overview, and usage example

#1 opened 8 months ago by

New activity in dongguanting/ARPO-RL-Reasoning-10K 8 months ago

Add `library_name: datasets` to metadata

#3 opened 8 months ago by

New activity in dongguanting/Qwen2.5-7B-ARPO 8 months ago

Improve: Add Tool-Star citation to model card

#2 opened 8 months ago by

commented 2 papers 8 months ago

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Paper • 2508.07050 • Published Aug 9, 2025 • 118 •

Agentic Reinforced Policy Optimization

Paper • 2507.19849 • Published Jul 26, 2025 • 160 •

New activity in dongguanting/Qwen2.5-7B-ARPO 8 months ago

Enhance model card for ARPO checkpoint with comprehensive details

#1 opened 8 months ago by