TianXiaoyu's picture

TianXiaoyu

Emperorizzis

·

Emperorizzis

AI & ML interests

Natural Language Processing, Large Language Model, Reinforcement Learning

Recent Activity

upvoted a paper 4 days ago

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

authored a paper 5 days ago

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

authored a paper 5 days ago

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

View all activity

Organizations

upvoted a paper 4 days ago

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published 7 days ago • 235

authored 2 papers 5 days ago

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

Paper • 2505.02142 • Published May 4, 2025

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 9 days ago • 56

New activity in Emperorizzis/ASTRA-32B-Thinking-v1 6 days ago

Add library_name and pipeline_tag metadata

#1 opened 8 days ago by

New activity in Emperorizzis/ASTRA-14B-Thinking-v1 6 days ago

Add library_name, pipeline_tag and arxiv metadata

#1 opened 8 days ago by

New activity in Emperorizzis/ASTRA-SFT-1k 6 days ago

Add task category and improve metadata

#1 opened 8 days ago by

New activity in Emperorizzis/ASTRA-RL-1k 6 days ago

Improve dataset card: Add task category, tags, and update paper link

#2 opened 8 days ago by

commented a paper 6 days ago

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 9 days ago • 56 •

upvoted a paper 6 days ago

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 9 days ago • 56

submitted a paper to Daily Papers 6 days ago

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 9 days ago • 56

updated 2 models 9 days ago

Emperorizzis/ASTRA-32B-Thinking-v1

Text Generation • 33B • Updated 6 days ago • 39 • 6

Emperorizzis/ASTRA-14B-Thinking-v1

Text Generation • 15B • Updated 6 days ago • 33 • 8

updated 2 datasets 9 days ago

Emperorizzis/ASTRA-SFT-1k

Viewer • Updated 6 days ago • 1k • 635 • 14

Emperorizzis/ASTRA-RL-1k

Viewer • Updated 6 days ago • 1k • 365 • 9

published 2 models 17 days ago

Emperorizzis/ASTRA-32B-Thinking-v1

Text Generation • 33B • Updated 6 days ago • 39 • 6

Emperorizzis/ASTRA-14B-Thinking-v1

Text Generation • 15B • Updated 6 days ago • 33 • 8

published 2 datasets 17 days ago

Emperorizzis/ASTRA-SFT-1k

Viewer • Updated 6 days ago • 1k • 635 • 14

Emperorizzis/ASTRA-RL-1k

Viewer • Updated 6 days ago • 1k • 365 • 9

updated a collection 17 days ago

ASTRA Dataset

2 items • Updated 17 days ago • 4