KABI

dongguanting's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 1 day ago

RL+reason model

Collection

216 items • Updated 2 days ago • 16

upvoted a paper 4 days ago

RecGPT Technical Report

Paper • 2507.22879 • Published 7 days ago • 27

upvoted a paper 5 days ago

Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving

Paper • 2507.23726 • Published 6 days ago • 96

upvoted a paper 6 days ago

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Paper • 2507.21809 • Published 8 days ago • 111

commented a paper 7 days ago

Agentic Reinforced Policy Optimization

Paper • 2507.19849 • Published 11 days ago • 127 •

7

upvoted a paper 8 days ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published 13 days ago • 267

authored 4 papers 8 days ago

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation

Paper • 2505.10413 • Published May 15

Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation

Paper • 2506.21384 • Published Jun 26

Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search

Paper • 2507.02652 • Published Jul 3 • 24

Agentic Reinforced Policy Optimization

Paper • 2507.19849 • Published 11 days ago • 127

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

Enhance model card for ARPO checkpoint with comprehensive details

#1 opened 8 days ago by

nielsr

New activity in dongguanting/ARPO-RL-DeepSearch-1K 8 days ago

Improve dataset card for ARPO: Add metadata and detailed content

#1 opened 8 days ago by

nielsr

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

Enhance dataset card with metadata, abstract, and usage examples

#1 opened 8 days ago by

nielsr

updated 3 datasets 8 days ago

dongguanting/ARPO-RL-DeepSearch-1K

Viewer • Updated 8 days ago • 1.07k • 172 • 2

dongguanting/ARPO-RL-Reasoning-10K

Viewer • Updated 8 days ago • 10k • 161 • 1

dongguanting/ARPO-SFT-54K

Viewer • Updated 8 days ago • 54.6k • 347 • 7

updated 4 models 8 days ago

dongguanting/Qwen3-14B-ARPO-DeepSearch

15B • Updated 8 days ago • 12 • 3

dongguanting/Qwen3-8B-ARPO-DeepSearch

8B • Updated 8 days ago • 10 • 1

dongguanting/Llama3.1-8B-ARPO

8B • Updated 8 days ago • 4 • 1

dongguanting/Qwen2.5-7B-ARPO

Text Generation • 8B • Updated 8 days ago • 17 • 2