4 papers
Disentangling Regional Primitives for Image Generation
Zhengting Chen, Lei Cheng, Lianghui Ding +2
This paper explains a neural network for image generation from a new perspective, i.e., explaining representation structures for image generation. We propose a set of desirable pro…
Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
Junpeng Zhang, Lei Cheng, Qing Li +2
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power. We also discover that the confusing samples…
Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
Siyu Lou, Yuntian Chen, Xiaodan Liang +2
In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language g…
Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
Junpeng Zhang, Qing Li, Liang Lin +1
This paper investigates the dynamics of a deep neural network (DNN) learning interactions. Previous studies have discovered and mathematically proven that given each input sample,…