Haoyu Wang

Harryis

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 30 days ago

AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?

liked a dataset about 2 months ago

LordNoah/ADB-data

updated a dataset about 2 months ago

Harryis/LWM_Phase1

View all activity

Organizations

Papers 4

arxiv:2601.21754

arxiv:2505.20259

arxiv:2404.05331

arxiv:2402.07610

models 3

Harryis/SCOUT_multitask

Reinforcement Learning • 3B • Updated Feb 1 • 5 • 2

Harryis/Genn_multi_task_qwen3_4b_it

Updated Sep 14, 2025

Harryis/llama3.1_8b_full_cot_scaledata_V4

Updated Jan 17, 2025

datasets 7

Harryis/LWM_Phase1

Updated Sep 9 • 5

Harryis/strategy

Updated Jul 28 • 27

Harryis/VAGEN

Updated Jul 28 • 127

Harryis/RAGEN_v2

Preview • Updated Jul 25 • 1.18k

Harryis/RAGEN

Updated Jul 24 • 2.35k

Harryis/LLaMAFactory

Preview • Updated Jul 23 • 153

Harryis/LifelongSA

Updated Feb 2 • 349