Taiwei Shi's picture

Taiwei Shi

MaksimSTW

·

https://maksimstw.github.io/

AI & ML interests

alignment, human-AI collaboration, and computational social science

Recent Activity

upvoted a paper about 4 hours ago

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

upvoted a collection about 5 hours ago

Papers from LIME Lab

new activity 5 days ago

lime-nlp/DeepScaleR_Difficulty:Request for sharing the rollout outputs for success rate calculation

View all activity

Organizations

MaksimSTW's activity

upvoted a paper about 4 hours ago

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Paper • 2504.10766 • Published 1 day ago • 14

upvoted a collection about 5 hours ago

Papers from LIME Lab

Papers from LIME Lab • 7 items • Updated 7 days ago • 2

New activity in lime-nlp/DeepScaleR_Difficulty 5 days ago

Request for sharing the rollout outputs for success rate calculation

#2 opened 5 days ago by

upvoted a paper 5 days ago

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Paper • 2504.07964 • Published 6 days ago • 58

updated 2 datasets 6 days ago

lime-nlp/DeepScaleR_Difficulty

Viewer • Updated 6 days ago • 5.06M • 61 • 2

lime-nlp/orz_math_difficulty

Viewer • Updated 6 days ago • 6.18M • 41

New activity in lime-nlp/GSM8K_Difficulty 6 days ago

Add task category and link to paper/Github repo

#1 opened 6 days ago by

updated a dataset 6 days ago

lime-nlp/MATH_Difficulty

Viewer • Updated 6 days ago • 1.61M • 44

New activity in lime-nlp/MATH_Difficulty 6 days ago

Add link to paper and Github repo

#2 opened 6 days ago by

New activity in lime-nlp/orz_math_difficulty 6 days ago

Add Github repo link and task category.

#1 opened 6 days ago by

New activity in lime-nlp/DeepScaleR_Difficulty 6 days ago

Add link to paper, task categories

#1 opened 6 days ago by

upvoted a paper 6 days ago

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Paper • 2504.06514 • Published 7 days ago • 33

commented a paper 7 days ago

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Paper • 2504.05520 • Published 8 days ago • 9 •

authored a paper 7 days ago

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Paper • 2504.05520 • Published 8 days ago • 9

updated 2 collections 7 days ago

Papers from LIME Lab

Papers from LIME Lab • 7 items • Updated 7 days ago • 2

Difficulty Estimation Math Datasets

We perform difficulty estimation on popular math datasets. • 5 items • Updated 7 days ago • 1

updated a dataset 7 days ago

lime-nlp/GSM8K_Difficulty

Viewer • Updated 7 days ago • 1.13M • 59

upvoted a paper 7 days ago

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Paper • 2504.05520 • Published 8 days ago • 9

published a dataset 7 days ago

lime-nlp/orz_math_difficulty

Viewer • Updated 6 days ago • 6.18M • 41

commented a paper 14 days ago

Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base

Paper • 2503.23361 • Published 17 days ago • 6 •