XuQixin's picture

5 3

XuQixin

Racktic

·

Racktic

AI & ML interests

NLP, mutimodel

Recent Activity

authored a paper 7 days ago

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

authored a paper 7 days ago

Reverse-Engineered Reasoning for Open-Ended Generation

upvoted a paper 8 days ago

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

View all activity

Organizations

None yet

Papers 3

arxiv:2509.06160

arxiv:2509.03646

arxiv:2502.01456

models 1

Racktic/qwen_dedup_top8_dpo_old_math_new_math_syn_olympiads

Updated Dec 16, 2024

datasets 11

Racktic/mathverse

Viewer • Updated Jul 2 • 3.94k • 6

Racktic/dynamath

Viewer • Updated Jul 2 • 5.01k • 5

Racktic/mathvista_0702

Viewer • Updated Jul 1 • 998 • 7

Racktic/VLMEvalKit

Updated Jun 28 • 276

Racktic/multimodal_rl_data_testset1

Viewer • Updated Jun 28 • 998 • 4

Racktic/multimodal_rl_data_testset

Viewer • Updated Jun 25 • 1.89k • 5

Racktic/multimodal_rl_data

Viewer • Updated Jun 24 • 81.9k • 16

Racktic/mmmu

Viewer • Updated Jun 24 • 894 • 6

Racktic/mathvista

Viewer • Updated Jun 24 • 998 • 7

Racktic/multimodal_math_80k

Viewer • Updated Jun 24 • 80k • 62

View 11 datasets