wujinzhu
kimjohn
ยท
AI & ML interests
Large Language Model, Natural Language Processing, Computer Vision
Recent Activity
upvoted
a
paper
about 8 hours ago
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning
Capabilities Through Evaluation Design
commented on
a paper
about 1 month ago
Does Reinforcement Learning Really Incentivize Reasoning Capacity in
LLMs Beyond the Base Model?
new activity
3 months ago
qihoo360/TinyR1-32B-Preview:What kind of model merge method do you use ?
Organizations
None yet
models
0
None public yet
datasets
0
None public yet