Li Erran Li

erranli

2 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 9 hours ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

updated a model 8 months ago

thinking-bio-lab/new_unimomo

published a model 8 months ago

thinking-bio-lab/new_unimomo

View all activity

Organizations

Papers 1

arxiv:2402.06118

models 5

erranli/rl-qwen2.5-7b-mot

Updated Sep 26, 2025

erranli/qwen2.5-7b-mot-grokking

Text Generation • Updated Sep 25, 2025 • 12

erranli/qwen2.5-7b-mot-full

Updated Sep 23, 2025 • 3

erranli/coder-ft-qwen2.5-7b

8B • Updated Sep 23, 2025 • 7

erranli/llama3_qa_model

Updated Nov 2, 2024

datasets 5

erranli/codeforces-cot-highquality

Viewer • Updated Sep 24, 2025 • 3.62k • 18

erranli/codeforces-benchmark-results

Updated Sep 23, 2025 • 132

erranli/deepcoder-train-success

Viewer • Updated Sep 22, 2025 • 13.6k • 8

erranli/deepcoder-train-traj

Updated Sep 22, 2025 • 10

erranli/codeforces-cot-filtered

Preview • Updated Sep 22, 2025 • 70