Wang's picture

Wang

pengkaiScience

·

pidneuralode

AI & ML interests

AI4Science, LLM, Symbolic regression

Recent Activity

commentedon a paper 6 days ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

upvoted a paper 6 days ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

upvoted a paper 26 days ago

Model Merging Scaling Laws in Large Language Models

View all activity

Organizations

commented a paper 6 days ago

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Paper • 2605.26844 • Published 12 days ago • 25 •

commented a paper 26 days ago

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

Paper • 2605.09608 • Published 28 days ago • 52 •

commented a paper 6 months ago

An Efficient Graph-Transformer Operator for Learning Physical Dynamics with Manifolds Embedding

Paper • 2512.10227 • Published Dec 11, 2025 • 2 •