PPaperPicks

Quanshi Zhang

12 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Challenging the Explanation Based on Preceding Tokens: Discovering Transferable Non-Literal Biasing
  2. Monitoring Primitive Interactions During the Training of DNNs
  3. Towards Attributions of Input Variables in a Coalition
  4. Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
  5. Batch Normalization Is Blind to the First and Second Derivatives of the Loss
  6. Clarifying the Behavior and the Difficulty of Adversarial Training
  7. Defining and extracting generalizable interaction primitives from DNNs
  8. Explaining Generalization Power of a DNN Using Interactive Concepts
  9. Identifying Semantic Induction Heads to Understand In-Context Learning
  10. Layerwise Change of Knowledge in Neural Networks
  11. Towards the Dynamics of a DNN Learning Symbolic Interactions
  12. Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs