Quanshi Zhang

Towards the Three-Phase Dynamics of Generalization Power of a DNN

Disentangling Primitive Representation Structures for Image Generation

Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment

Towards the Decisive Factor of Symbolic Generalization of DNNs

Quantifying QiGan: What Shape Patterns Does a DNN Exploit in Go?

Formulating Generalizable and Non-Generalizable Interactions in DNNs

Counting Hallucinations in Diffusion Models

Towards the Mysteries of Convergent Interaction Representations through DNNs

Towards the Dynamics of Representation Changes during Parameter Pruning for Network Compression

Towards the Resistance of Neural Network Fingerprinting to Fine-tuning

Towards Attributions of Input Variables in a Coalition

Disentangling Regional Primitives for Image Generation

Disentangling the QiGan Encoded by a DNN towards the Go Game

Alignment Between the Decision-Making Logic of LLMs and Human Cognition: A Case Study on Legal LLMs