Xiaolu Zhang

Deterministic Differentiable Structured Pruning for Large Language Models

Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplicative gate for each component under an $\ell_0$ sparsity constraint. Due to the discreteness of the $\ell_0$ norm, prior work typically adopts stochastic hard-…

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant in current multimodal approaches. Built upon LLaDA, a repres

Rapid and Hierarchical UAV Exploration Via Adaptive Regional Viewpoint Generation

BOSE: A Systematic Evaluation Method Optimized for Base Models

This paper poses two critical issues in evaluating base models (without post-training): (1) Unstable evaluation during training: in the early stages of pre-training, the models lack the capability to answer questions as required, leading to unstable evaluation results. This instability makes it diff…

Effective and Efficient Masked Image Generation Models

Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key facto…

Large Language Diffusion Models

The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing *LLaDA*, a diffusion model trained from scratch under the pre-training and supervised fine-tuning (SFT) paradigm. LLaDA employs a forward data mask…

NATRA: Noise-Agnostic Framework for Trajectory Prediction with Noisy Observations

Trajectory prediction aims to forecast an agent's future trajectories based on its historical observed trajectories, which is a critical task for various applications such as autonomous driving, robotics, and surveillance systems. Most existing trajectory prediction methods assume that the observed…

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries—a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative safety alignment, causing models to treat many reasonable prom

Efficient Model Stealing Defense with Noise Transition Matrix

With the escalating complexity and investment cost of training deep neural networks safeguarding them from unauthorized usage and intellectual property theft has become imperative. Especially the rampant misuse of prediction APIs to replicate models without access to the original data or architectur…

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Toke…

Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization

Gradient-based bilevel programming leverages unrolling differentiation (UD) or implicit function theorem (IFT) to solve hyperparameter optimization (HO) problems, and is proven effective and scalable in practice. To understand their generalization behavior, existing works establish upper bounds on…

Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models

Recently, various strategies for distributed training of large language models (LLMs) have been proposed. By categorizing them into basic strategies and composite strategies, we have discovered that existing basic strategies provide limited options in specific scenarios, leaving considerable room fo…

Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations

Bayesian flow networks (BFNs) iteratively refine the parameters, instead of the samples in diffusion models (DMs), of distributions at various noise levels through Bayesian inference. Owing to its differentiable nature, BFNs are promising in modeling both continuous and discrete data, while simultan…

Towards Open Temporal Graph Neural Networks

Graph neural networks (GNNs) for temporal graphs have recently attracted increasing attentions, where a common assumption is that the class set for nodes is closed. However, in real-world scenarios, it often faces the open set problem with the dynamically increased class set as the time passes by. T…

Attribute-Conditioned Face Swapping Network for Low-Resolution Images

Deep learning based face swapping technologies have opened new frontiers for entertainment industries while pose novel threats to identity security. Applying face swapping to real-world products, as well as defending against its misuse, rely on the capacity to generate high quality face swapped imag…

Learning Mixture of Neural Temporal Point Processes for Multi-dimensional Event Sequence Clustering

Multi-dimensional event sequence clustering applies to many scenarios e.g. e-Commerce and electronic health. Traditional clustering models fail to characterize complex real-world processes due to the strong parametric assumption. While Neural Temporal Point Processes (NTPPs) mainly focus on modeling…

Improving Transferability of Adversarial Patches on Face Recognition With Generative Models

Face recognition is greatly improved by deep convolutional neural networks (CNNs). Recently, these face recognition models have been used for identity authentication in security sensitive applications. However, deep CNNs are vulnerable to adversarial patches, which are physically realizable and stea…

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

Gradient estimation and vector space projection have been studied as two distinct topics. We aim to bridge the gap between the two by investigating how to efficiently estimate gradient based on a projected low-dimensional space. We first provide lower and upper bounds for gradient estimation under b…

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

Boundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional image data. In this paper, we show that such efficiency highly…

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Machine learning (ML), especially deep neural networks (DNNs) have been widely used in various applications, including several safety-critical ones (e.g. autonomous driving). As a result, recent research about adversarial examples has raised great concerns. Such adversarial attacks can be achieved b…

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the…

P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification

Recently, deep convolutional neural networks (CNNs) have achieved great success in pathological image classification. However, due to the limited number of labeled pathological images, there are still two challenges to be addressed: (1) overfitting: the performance of a CNN model is undermined by th…