Publications by Yongtao Wu | EPFL Graph Search

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, th ...

Accurately and rapidly simulating the hysteretic behavior of double skin composite wall (DSCW) under earthquake loads enhance the efficiency of seismic performance assessments for high-rise steel-concrete composite structures. The application of artificial ...

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

In this paper, we aim to build the global convergence theory of encoder-only shallow Transformers under a realistic setting from the perspective of architectures, initialization, and scaling under a finite width regime. The difficulty lies in how to tackle ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

Defending aligned Large Language Models (LLMs) against jailbreaking attacks is a challenging problem, with existing approaches requiring multiple requests or even queries to auxiliary LLMs, making them computationally heavy. Instead, we focus on detecting ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

We develop universal gradient methods for Stochastic Convex Optimization (SCO). Our algorithms automatically adapt not only to the oracle's noise but also to the Hölder smoothness of the objective function without a priori knowledge of the particular setti ...

Yongtao Wu

Chat with Graph Search

Hadamard product in deep learning: Introduction, Advances and Challenges

Machine learning-aided hysteretic response prediction of double skin composite wall under earthquake loads

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

On the Convergence of Encoder-only Shallow Transformers

Revisiting Character-level Adversarial Attacks for Language Models

Single-pass Detection of Jailbreaking Input in Large Language Models

Robust NAS under adversarial training: benchmark, theory, and beyond

Universal Gradient Methods for Stochastic Convex Optimization