1 citations · 1 across the 6 of their papers we have counts for
7 papers
Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation
Xiahui Zhu, Zhenyi Qi, Wanwei Liu +4
Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional probability models that lear…
Shapley-Guided Neural Repair Approach via Derivative-Free Optimization
Xinyu Sun, Wanwei Liu, Haoang Chi +7
DNNs are susceptible to defects like backdoors, adversarial attacks, and unfairness, undermining their reliability. Existing approaches mainly involve retraining, optimization, con…
UR4NNV: Neural Network Verification, Under-approximation Reachability Works!
Zhen Liang, Taoran Wu, Ran Zhao +5
Recently, formal verification of deep neural networks (DNNs) has garnered considerable attention, and over-approximation based methods have become popular due to their effectivenes…
An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks
Ye Tao, Wanwei Liu, Fu Song +3
Deep neural networks, (DNNs, a.k.a. NNs), have been widely used in various tasks and have been proven to be successful. However, the accompanied expensive computing and storage cos…
Verifying Safety of Neural Networks from Topological Perspectives
Zhen Liang, Dejin Ren, Bai Xue +3
Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their beha…
Repairing Deep Neural Networks Based on Behavior Imitation
Zhen Liang, Taoran Wu, Changyuan Zhao +4
The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and test…
Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory
Zhen Liang, Changyuan Zhao, Wanwei Liu +3
Credit assignment problem of neural networks refers to evaluating the credit of each network component to the final outputs. For an untrained neural network, approaches to tackling…