Xirui Li's picture

Xirui Li PRO

AIcell

·

https://xirui-li.github.io/

AI & ML interests

Foundation LLM and VLM

Recent Activity

upvoted a paper 6 days ago

The Path Not Taken: RLVR Provably Learns Off the Principals

upvoted a paper 10 days ago

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

upvoted a paper 18 days ago

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

View all activity

Organizations

Papers 1

arxiv:2503.05132

models 26

AIcell/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-Majority

2B • Updated 19 days ago • 25

AIcell/Qwen-1.5B-Instruct-GRPO-Majority

2B • Updated 22 days ago • 8

AIcell/Qwen-1.5B-Instruct-GRPO-Random

2B • Updated 22 days ago • 11

AIcell/Qwen-1.5B-Instruct-GRPO

2B • Updated 22 days ago • 9

AIcell/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-non-reasoning

2B • Updated 29 days ago • 28

AIcell/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-opposite

2B • Updated 29 days ago • 10

AIcell/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-random

2B • Updated Oct 21 • 2

AIcell/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

2B • Updated Oct 17 • 2

AIcell/Qwen2.5-1.5B-Instruct-GRPO-gsm8k

Text Generation • 2B • Updated Oct 13 • 12

AIcell/Qwen2.5-0.5B-Instruct-GRPO-gsm8k

Text Generation • 0.5B • Updated Oct 13 • 5

datasets 2

AIcell/unified-text-rendering

Viewer • Updated Aug 3 • 20.7k • 26 • 1

AIcell/MOSSBench

Updated Mar 4 • 230 • 5