Xingwei Tan

XingweiT

13 32 30

Xingwei-Tan

AI & ML interests

None yet

Recent Activity

authored a paper about 3 hours ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

upvoted a paper 4 days ago

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

upvoted a paper 8 days ago

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

View all activity

Organizations

None yet

Collections 2

Papers 11

models 0

None public yet

datasets 4

Xingwei Tan

AI & ML interests

Recent Activity

Organizations

Collections 2

Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision

XingweiT/SymbReAct-trace-dpo

XingweiT/SymbReAct-trace-sft

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

XingweiT/IntrEx-sequence

XingweiT/IntrEx-turn

Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision

XingweiT/SymbReAct-trace-dpo

XingweiT/SymbReAct-trace-sft

IntrEx: A Dataset for Modeling Engagement in Educational Conversations

XingweiT/IntrEx-sequence

XingweiT/IntrEx-turn

Papers 11

models 0

datasets 4

XingweiT/SymbReAct-trace-sft

XingweiT/SymbReAct-trace-dpo

XingweiT/IntrEx-sequence

XingweiT/IntrEx-turn

Xingwei Tan

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 11

models 0

datasets 4 Sort: Recently updated

datasets 4