Junnan Liu

jnanliu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 7 days ago

jnanliu/orz-math-filtered

Viewer • Updated 7 days ago • 39.7k • 72

published a dataset 7 days ago

jnanliu/orz-math-filtered

Viewer • Updated 7 days ago • 39.7k • 72

updated a dataset 7 days ago

jnanliu/NuminaMath-1.5-550k

Viewer • Updated 7 days ago • 548k • 15

published a dataset 7 days ago

jnanliu/NuminaMath-1.5-550k

Viewer • Updated 7 days ago • 548k • 15

updated a dataset 9 days ago

opencompass/LiveMathBench

Viewer • Updated 9 days ago • 283 • 792 • 4

upvoted a paper 10 days ago

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

Paper • 2502.18411 • Published 10 days ago • 69

published a dataset 12 days ago

jnanliu/orz-math-57k

Viewer • Updated 12 days ago • 56.9k • 152

updated a dataset 12 days ago

jnanliu/orz-math-57k

Viewer • Updated 12 days ago • 56.9k • 152

liked a dataset 12 days ago

nvidia/AceMath-Instruct-Training-Data

Viewer • Updated Jan 17 • 5.56M • 1.75k • 45

liked a dataset 24 days ago

open-r1/OpenR1-Math-220k

Viewer • Updated 17 days ago • 450k • 42.7k • 472

upvoted a paper 24 days ago

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Paper • 2502.06781 • Published 25 days ago • 60

upvoted a paper about 1 month ago

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement

Paper • 2501.12273 • Published Jan 21 • 14

liked 7 models about 2 months ago

deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Text Generation • Updated 12 days ago • 435k • • 617

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

Text Generation • Updated 12 days ago • 636k • • 455

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Text Generation • Updated 12 days ago • 1.51M • • 630

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Text Generation • Updated 12 days ago • 1.09M • 530

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 12 days ago • 1.47M • • 998

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Text Generation • Updated 12 days ago • 1.47M • • 1.23k

deepseek-ai/DeepSeek-R1

Text Generation • Updated 12 days ago • 4.16M • • 10.9k

updated a dataset about 2 months ago

opencompass/LiveMathBench

Viewer • Updated 9 days ago • 283 • 792 • 4