Xingwei Tan

XingweiT

·

Xingwei-Tan

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

upvoted a paper 7 days ago

Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior

upvoted a paper 2 months ago

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility

View all activity

Organizations

None yet

XingweiT 's models

None public yet