Kuo-Hsin Tu PRO
dapumptu
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 21 hours ago
Are We on the Right Way to Assessing LLM-as-a-Judge?
upvoted
a
paper
2 days ago
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
upvoted
a
paper
2 days ago
Rethinking Expert Trajectory Utilization in LLM Post-training
Organizations
-
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 127 -
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
Paper • 2405.04324 • Published • 25 -
Seed-Coder: Let the Code Model Curate Data for Itself
Paper • 2506.03524 • Published • 6 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 152
-
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 127 -
Granite Code Models: A Family of Open Foundation Models for Code Intelligence
Paper • 2405.04324 • Published • 25 -
Seed-Coder: Let the Code Model Curate Data for Itself
Paper • 2506.03524 • Published • 6 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 152
datasets
0
None public yet