6 citations · 13 across the 12 of their papers we have counts for
11 papers · 1 filter
From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias
Yongtao Wu, Mahdi Mansouri, Zhenyu Zhu
Prior work on implicit bias shows that gradient descent selects the Frobenius max-margin direction on linearly separable problems, whereas Fan et al. (2025) established spectral ma…
Robustness in Both Domains: CLIP Needs a Robust Text Encoder
Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh +3
Adversarial input attacks can cause a significant shift of CLIP embeddings. This can affect the downstream robustness of models incorporating CLIP in the pipeline, such as text-to-…
Hadamard product in deep learning: Introduction, Advances and Challenges
Grigorios G Chrysos, Yongtao Wu, Razvan Pascanu +2
While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard pr…
Quantum-PEFT: Ultra parameter-efficient fine-tuning
Toshiaki Koike-Akino, Francesco Tonin, Yongtao Wu +3
This paper introduces Quantum-PEFT that leverages quantum computations for parameter-efficient fine-tuning (PEFT). Unlike other additive PEFT methods, such as low-rank adaptation (…
Single-pass Detection of Jailbreaking Input in Large Language Models
Leyla Naz Candogan, Yongtao Wu, Elias Abad Rocamora +2
Defending aligned Large Language Models (LLMs) against jailbreaking attacks is a challenging problem, with existing approaches requiring multiple requests or even queries to auxili…
Linear Attention for Efficient Bidirectional Sequence Modeling
Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan +5
Linear Transformers and State Space Models have emerged as efficient alternatives to softmax Transformers for causal sequence modeling, enabling parallel training via matrix multip…
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
Yongtao Wu, Luca Viano, Yihang Chen +4
Reinforcement Learning from Human Feedback (RLHF) has been highly successful in aligning large language models with human preferences. While prevalent methods like DPO have demonst…
Revisiting Character-level Adversarial Attacks for Language Models
Elias Abad Rocamora, Yongtao Wu, Fanghui Liu +2
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 met…
Robust NAS under adversarial training: benchmark, theory, and beyond
Yongtao Wu, Fanghui Liu, Carl-Johann Simon-Gabriel +2
Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence o…
On the Convergence of Encoder-only Shallow Transformers
Yongtao Wu, Fanghui Liu, Grigorios G Chrysos +1
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, a…
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Yongtao Wu, Zhenyu Zhu, Fanghui Liu +2
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…