8 6 5

Qian Dong

qian

https://dongqian.bj.cn/

AI & ML interests

Information retrieval

Recent Activity

upvoted a paper about 1 month ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

authored a paper 5 months ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

liked a model 5 months ago

zai-org/GLM-4.5V

View all activity

Organizations

upvoted a paper about 1 month ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published Dec 1, 2025 • 95

authored a paper 5 months ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published Aug 8, 2025 • 195

liked a model 5 months ago

zai-org/GLM-4.5V

Image-Text-to-Text • 108B • Updated Oct 25, 2025 • 35k • • 700

upvoted a paper 5 months ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published Aug 8, 2025 • 195

liked a model 5 months ago

zai-org/GLM-4.5

Text Generation • 358B • Updated Aug 11, 2025 • 21.5k • • 1.39k

upvoted a paper 5 months ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24, 2025 • 316

updated a dataset 9 months ago

THUIR/Qilin

Viewer • Updated Apr 17, 2025 • 2.15M • 984 • 29

New activity in THUIR/Qilin 10 months ago

Add Github link and task category

#3 opened 10 months ago by

nielsr

updated a dataset 10 months ago

THUIR/T2Ranking

Updated Mar 6, 2025 • 649 • 32

New activity in THUIR/Qilin 10 months ago

Add link to paper, task categories

#2 opened 10 months ago by

nielsr

reacted to AdinaY's post with 🔥 10 months ago

Post

1723

Qilin 🔥a large scale multimodal dataset for search, recommendation and RAG research, released by Xiaohongshu & Tsinghua University

Dataset: THUIR/Qilin
Paper: Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions (2503.00501)

✨Multiple content modalities (text, images, video thumbnails)
✨Rich user interaction data ( from Xiaohongshu’s 300M+ MAUs, 70%+ search penetration)
✨Comprehensive evaluation metrics
✨Support for RAG system development