Longxu Dou's picture

Longxu Dou

dreamerdeo

·

https://longxudou.github.io/

AI & ML interests

Natural Language Processing

Recent Activity

commented on a paper 21 minutes ago

Kuwain 1.5B: An Arabic SLM via Language Injection

upvoted a paper 1 day ago

Could Thinking Multilingually Empower LLM Reasoning?

authored a paper 1 day ago

FlowReasoner: Reinforcing Query-Level Meta-Agents

View all activity

Organizations

dreamerdeo's activity

commented a paper 21 minutes ago

Kuwain 1.5B: An Arabic SLM via Language Injection

Paper • 2504.15120 • Published 2 days ago • 89 •

upvoted a paper 1 day ago

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published 7 days ago • 25

authored a paper 1 day ago

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 2 days ago • 41

upvoted a paper 1 day ago

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 2 days ago • 41

upvoted a collection 3 days ago

NoisyRollout

6 items • Updated about 6 hours ago • 5

authored a paper 5 days ago

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

Paper • 2504.13055 • Published 6 days ago • 18

upvoted a paper 5 days ago

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

Paper • 2504.13055 • Published 6 days ago • 18

commented a paper 5 days ago

NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

Paper • 2504.13055 • Published 6 days ago • 18 •

authored 2 papers 7 days ago

SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types

Paper • 2412.11757 • Published Dec 16, 2024

Efficient Process Reward Model Training via Active Learning

Paper • 2504.10559 • Published 9 days ago • 13

upvoted a collection 7 days ago

🚀 Active PRM

Efficient Process Reward Model Training via Active Learning. • 4 items • Updated 8 days ago • 3

upvoted a paper 8 days ago

Understanding R1-Zero-Like Training: A Critical Perspective

Paper • 2503.20783 • Published 28 days ago • 45

upvoted a collection 8 days ago

🌾Oat-Zero: Understanding R1-Zero-Like Training

5 items • Updated 14 days ago • 7

upvoted a paper 8 days ago

Efficient Process Reward Model Training via Active Learning

Paper • 2504.10559 • Published 9 days ago • 13

updated a collection 8 days ago

🚀 Active PRM

Efficient Process Reward Model Training via Active Learning. • 4 items • Updated 8 days ago • 3

commented a paper 8 days ago

Efficient Process Reward Model Training via Active Learning

Paper • 2504.10559 • Published 9 days ago • 13 •

New activity in sailor2/sea-wildbench 27 days ago

[bot] Conversion to Parquet

#2 opened 28 days ago by

parquet-converter

updated a dataset 28 days ago

sailor2/sea-wildbench

Viewer • Updated 28 days ago • 1.02k • 63

updated a Space about 1 month ago

README