Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 7 hours ago
ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
upvoted
a
paper
about 20 hours ago
ReasonIF: Large Reasoning Models Fail to Follow Instructions During
Reasoning
upvoted
a
paper
about 21 hours ago
olmOCR 2: Unit Test Rewards for Document OCR
Organizations
None yet