Yidan Shi

DannieSYD

2

·

AI & ML interests

Generative & Agentic AI

Recent Activity

upvoted a paper about 20 hours ago

ACLArena: Agent Continue Learning in Multi-stage Post-training

upvoted a paper 7 months ago

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

updated a dataset 7 months ago

DannieSYD/FraMe-Ala4

View all activity

Organizations

DannieSYD 's models 4

DannieSYD/Qwen3-VL-4B-Instruct-sft-with-visual

4B • Updated Jan 10 • 13

DannieSYD/Qwen3-VL-4B-Instruct-merged

4B • Updated Dec 22, 2025 • 6

DannieSYD/Qwen3-VL-4B-Instruct-trl-sft

Updated Dec 22, 2025

DannieSYD/Merged_Qwen3_VL_4B_OLD_only_text

4B • Updated Nov 20, 2025 • 5