Arrow Research search

Author name cluster

Xue Jiang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

16 papers
2 author rows

Possible papers

16

AAAI Conference 2026 Conference Paper

Large Language Model Unlearning for Source Code

  • Xue Jiang
  • Yihong Dong
  • Huangzhao Zhang
  • Tangxinyu Wang
  • Zheng Fang
  • Yingwei Ma
  • Rongyu Cao
  • Binhua Li

While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringement, insecurity emission, and deprecated API utilization, etc. A straightforward yet promising defense is unlearning, i.e., erasing or down-weighting the offending snippets through post-training. However, we find its application to source code often tends to spill over, damaging the basic knowledge of programming languages learned by the LLM and degrading the overall capability. To ease this challenge, we propose PROD for precise source code unlearning. PROD surgically zeroes out the prediction probability of the prohibited tokens, and renormalizes the remaining distribution so that the generated code stays correct. By excising only the targeted snippets, PROD achieves precise forgetting without much degradation of the LLM's overall capability. To facilitate in-depth evaluation against PROD, we establish an unlearning benchmark consisting of three downstream tasks (i.e., unlearning of copyrighted code, insecure code, and deprecated APIs), and introduce Pareto Dominance Ratio (PDR) metric, which indicates both the forget quality and the LLM utility. Our comprehensive evaluation demonstrates that PROD achieves superior overall performance between forget quality and model utility compared to existing unlearning approaches across three downstream tasks, while consistently exhibiting improvements when applied to LLMs of varying series. PROD also exhibits superior robustness against adversarial attacks without generating or exposing the data to be forgotten. These results underscore that our approach not only successfully extends the application boundary of unlearning techniques to source code, but also holds significant implications for advancing reliable code generation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach

  • Linhao Huang
  • Xue Jiang
  • Zhiqiang Wang
  • Wentao Mo
  • Xi Xiao
  • Yong-Jie Yin
  • Bo Han
  • Feng Zheng

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models—a common and practical real-world scenario—remains unexplored. In this paper, we pioneer an investigation into the transferability of adversarial video samples across V-MLLMs. We find that existing adversarial attack methods face significant limitations when applied in black-box settings for V-MLLMs, which we attribute to the following shortcomings: (1) lacking generalization in perturbing video features, (2) focusing only on sparse key-frames, and (3) failing to integrate multimodal information. To address these limitations and deepen the understanding of V-MLLM vulnerabilities in black-box scenarios, we introduce the Image-to-Video MLLM (I2V-MLLM) attack. In I2V-MLLM, we utilize an image-based multimodal large language model (I-MLLM) as a surrogate model to craft adversarial video samples. Multimodal interactions and spatiotemporal information are integrated to disrupt video representations within the latent space, improving adversarial transferability. Additionally, a perturbation propagation technique is introduced to handle different unknown frame sampling strategies. Experimental results demonstrate that our method can generate adversarial examples that exhibit strong transferability across different V-MLLMs on multiple video-text multimodal tasks. Compared to white-box attacks on these models, our black-box attacks (using BLIP-2 as a surrogate model) achieve competitive performance, with average attack success rate (AASR) of 57.98% on MSVD-QA and 58.26% on MSRVTT-QA for Zero-Shot VideoQA tasks, respectively.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

FAN: Fourier Analysis Networks

  • Yihong Dong
  • Ge Li
  • Yongding Tao
  • Xue Jiang
  • Kechi Zhang
  • Jia Li
  • Jinliang Deng
  • Jing Su

Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about periodic phenomena, achieving only marginal performance within the training domain and failing to generalize effectively to out-of-domain (OOD) scenarios. Periodicity is ubiquitous throughout nature and science. Therefore, neural networks should be equipped with the essential ability to model and handle periodicity. In this work, we propose FAN, a novel neural network that effectively addresses periodicity modeling challenges while offering broad applicability similar to MLP with fewer parameters and FLOPs. Periodicity is naturally integrated into FAN's structure and computational processes by introducing the Fourier Principle. Unlike existing Fourier-based networks, which possess particular periodicity modeling abilities but face challenges in scaling to deeper networks and are typically designed for specific tasks, our approach overcomes this challenge to enable scaling to large-scale models and maintains the capability to be applied to more types of tasks. Through extensive experiments, we demonstrate the superiority of FAN in periodicity modeling tasks and the effectiveness and generalizability of FAN across a range of real-world tasks. Moreover, we reveal that compared to existing Fourier-based networks, FAN accommodates both periodicity modeling and general-purpose modeling well.

PDF Details

ICML Conference 2025 Conference Paper

On the Generalization Ability of Next-Token-Prediction Pretraining

  • Zhihao Li
  • Xue Jiang
  • Liyuan Liu
  • Xuelin Zhang
  • Hong Chen 0004
  • Feng Zheng 0001

Large language models (LLMs) have demonstrated remarkable potential in handling natural language processing (NLP) tasks and beyond. LLMs usually can be categorized as transformer decoder-only models (DOMs), utilizing Next-Token-Prediction (NTP) as their pre-training methodology. Despite their tremendous empirical successes, the theoretical understanding of how NTP pre-training affects the model’s generalization behavior is lacking. To fill this gap, we establish the fine-grained generalization analysis for NTP pre-training based on Rademacher complexity, where the dependence between tokens is also addressed. Technically, a novel decomposition of Rademacher complexity is developed to study DOMs from the representation learner and the token predictor, respectively. Furthermore, the upper bounds of covering number are established for multi-layer and multi-head transformer-decoder models under the Frobenius norm, which theoretically pioneers the incorporation of mask matrix within the self-attention mechanism. Our results reveal that the generalization ability of NTP pre-training is affected quantitively by the number of token sequences $N$, the maximum length of sequence $m$, and the count of parameters in the transformer model $\Theta$. Additionally, experiments on public datasets verify our theoretical findings.

Details

NeurIPS Conference 2025 Conference Paper

Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling

  • Yihong Dong
  • Ge Li
  • Xue Jiang
  • Yongding Tao
  • Kechi Zhang
  • Lecheng Wang
  • Hao Zhu
  • Huanyu Liu

Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within human learning paradigms. However, the potential flaws of periodicity modeling in Transformer affect the learning efficiency and establishment of underlying principles from data for large language models (LLMs) built upon it. In this paper, we demonstrate that integrating effective periodicity modeling can improve the learning efficiency and performance of LLMs. We introduce FANformer, which adapts Fourier Analysis Network (FAN) into attention mechanism to achieve efficient periodicity modeling, by modifying the feature projection process of attention mechanism. Extensive experimental results on language modeling show that FANformer consistently outperforms Transformer when scaling up model size and training tokens, underscoring its superior learning efficiency. Our pretrained FANformer-1B exhibits marked improvements on downstream tasks compared to open-source LLMs with similar model parameters or training tokens. Moreover, we reveal that FANformer exhibits superior ability to learn and apply rules for reasoning compared to Transformer. The results position FANformer as an effective and promising architecture for advancing LLMs.

PDF Details

AAAI Conference 2024 Conference Paper

Generalize for Future: Slow and Fast Trajectory Learning for CTR Prediction

  • Jian Zhu
  • Congcong Liu
  • Xue Jiang
  • Changping Peng
  • Zhangang Lin
  • Jingping Shao

Deep neural networks (DNNs) have achieved significant advancements in click-through rate (CTR) prediction by demonstrating strong generalization on training data. However, in real-world scenarios, the assumption of independent and identically distributed (i.i.d.) conditions, which is fundamental to this problem, is often violated due to temporal distribution shifts. This violation can lead to suboptimal model performance when optimizing empirical risk without access to future data, resulting in overfitting on the training data and convergence to a single sharp minimum. To address this challenge, we propose a novel model updating framework called Slow and Fast Trajectory Learning (SFTL) network. SFTL aims to mitigate the discrepancy between past and future domains while quickly adapting to recent changes in small temporal drifts. This mechanism entails two interactions among three complementary learners: (i) the Working Learner, which updates model parameters using modern optimizers (e.g., Adam, Adagrad) and serves as the primary learner in the recommendation system, (ii) the Slow Learner, which is updated in each temporal domain by directly assigning the model weights of the working learner, and (iii) the Fast Learner, which is updated in each iteration by assigning exponentially moving average weights of the working learner. Additionally, we propose a novel rank-based trajectory loss to facilitate interaction between the working learner and trajectory learner, aiming to adapt to temporal drift and enhance performance in the current domain compared to the past. We provide theoretical understanding and conduct extensive experiments on real-world CTR prediction datasets to validate the effectiveness and efficiency of SFTL in terms of both convergence speed and model performance. The results demonstrate the superiority of SFTL over existing approaches.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Negative Label Guided OOD Detection with Pretrained Vision-Language Models

  • Xue Jiang
  • Feng Liu 0003
  • Zhen Fang 0001
  • Hong Chen 0004
  • Tongliang Liu
  • Feng Zheng 0001
  • Bo Han 0003

Out-of-distribution (OOD) detection aims at identifying samples from unknown classes, playing a crucial role in trustworthy models against errors on unexpected inputs. Extensive research has been dedicated to exploring OOD detection in the vision modality. {Vision-language models (VLMs) can leverage both textual and visual information for various multi-modal applications, whereas few OOD detection methods take into account information from the text modality. In this paper, we propose a novel post hoc OOD detection method, called NegLabel, which takes a vast number of negative labels from extensive corpus databases. We design a novel scheme for the OOD score collaborated with negative labels. Theoretical analysis helps to understand the mechanism of negative labels. Extensive experiments demonstrate that our method NegLabel achieves state-of-the-art performance on various OOD detection benchmarks and generalizes well on multiple VLM architectures. Furthermore, our method NegLabel exhibits remarkable robustness against diverse domain shifts. The codes are available at https://github.com/tmlr-group/NegLabel.

Details

ECAI Conference 2023 Conference Paper

Antecedent Predictions Are More Important Than You Think: An Effective Method for Tree-Based Code Generation

  • Yihong Dong
  • Ge Li 0001
  • Xue Jiang
  • Zhi Jin 0001

Code generation focuses on automatically converting natural language (NL) utterances into code snippets. Sequence-to-tree (Seq2Tree) approaches are proposed for code generation with the aim of ensuring grammatical correctness of the generated code. These approaches generate subsequent Abstract Syntax Tree (AST) nodes based on the preceding predictions of AST nodes. However, existing Seq2Tree approaches tend to treat both antecedent predictions and subsequent predictions equally, which poses a challenge for models to produce accurate subsequent predictions if the antecedent predictions are incorrect under the constraints of the AST. Given this challenge, it is necessary to pay more attention to antecedent predictions compared to subsequent predictions. To this end, this paper proposes a novel and effective method, named Antecedent Prioritized (AP) Loss, which prioritizes antecedent predictions by leveraging the position information of the generated AST nodes. We design an AST-to-Vector (AST2Vec) method that maps AST node positions to two-dimensional vectors, thereby modeling the position information of AST nodes. To evaluate the effectiveness of our proposed loss, we implement and train an Antecedent Prioritized Tree-based code generation model called APT. Experiments on four benchmark datasets demonstrate that with better antecedent predictions and accompanying subsequent predictions, APT achieves significant improvements, indicating the superiority and generality of our proposed method.

Details

ICML Conference 2023 Conference Paper

Detecting Out-of-distribution Data through In-distribution Class Prior

  • Xue Jiang
  • Feng Liu 0003
  • Zhen Fang 0001
  • Hong Chen 0004
  • Tongliang Liu
  • Feng Zheng 0001
  • Bo Han 0003

Given a pre-trained in-distribution (ID) model, the inference-time out-of-distribution (OOD) detection aims to recognize OOD data during the inference stage. However, some representative methods share an unproven assumption that the probability that OOD data belong to every ID class should be the same, i. e. , these OOD-to-ID probabilities actually form a uniform distribution. In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model. Extensive experiments show that both strategies can improve the OOD detection performance when the ID model is pre-trained with imbalanced data, reflecting the importance of ID-class prior in OOD detection.

Details

AAAI Conference 2023 Conference Paper

On the Stability and Generalization of Triplet Learning

  • Jun Chen
  • Hong Chen
  • Xue Jiang
  • Bin Gu
  • Weifu Li
  • Tieliang Gong
  • Feng Zheng

Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then obtain the excess risk bounds of the order O(log(n)/(√n) ) for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where 2n is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as O(1/n) is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning.

PDF Details DOI

TIST Journal 2022 Journal Article

SignDS-FL: Local Differentially Private Federated Learning with Sign-based Dimension Selection

  • Xue Jiang
  • Xuebing Zhou
  • Jens Grossklags

Federated Learning (FL) [ 31 ] is a decentralized learning mechanism that has attracted increasing attention due to its achievements in computational efficiency and privacy preservation. However, recent research highlights that the original FL framework may still reveal sensitive information of clients’ local data from the exchanged local updates and the global model parameters. Local Differential Privacy (LDP), as a rigorous definition of privacy, has been applied to Federated Learning to provide formal privacy guarantees and prevent potential privacy leakage. However, previous LDP-FL solutions suffer from considerable utility loss with an increase of model dimensionality. Recent work [ 29 ] proposed a two-stage framework that mitigates the dimension-dependency problem by first selecting one “important” dimension for each local update and then perturbing the dimension value to construct the sparse privatized update. However, the framework may still suffer from utility loss because of the insufficient per-stage privacy budget and slow model convergence. In this article, we propose an improved framework, SignDS-FL, which shares the concept of dimension selection with Reference [ 29 ], but saves the privacy cost for the value perturbation stage by assigning random sign values to the selected dimensions. Besides using the single-dimension selection algorithms in Reference [ 29 ], we propose an Exponential Mechanism-based Multi-Dimension Selection algorithm that further improves model convergence and accuracy. We evaluate the framework on a number of real-world datasets with both simple logistic regression models and deep neural networks. For training logistic regression models on structured datasets, our framework yields only a \( \sim \) 1%–2% accuracy loss in comparison to a \( \sim \) 5%–15% decrease of accuracy for the baseline methods. For training deep neural networks on image datasets, the accuracy loss of our framework is less than \( 8\% \) and at best only \( 2\% \). Extensive experimental results show that our framework significantly outperforms the previous LDP-FL solutions and enjoys an advanced utility-privacy balance.

Details DOI

UAI Conference 2021 Conference Paper

TreeBERT: A tree-based pre-trained model for programming language

  • Xue Jiang
  • Zhuoran Zheng
  • Chen Lyu 0001
  • Liang Li
  • Lei Lyu 0001

Source code can be parsed into the abstract syntax tree (AST) based on defined syntax rules. However, in pre-training, little work has considered the incorporation of tree structure into the learning process. In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks. To utilize tree structure, TreeBERT represents the AST corresponding to the code as a set of composition paths and introduces node position embedding. The model is trained by tree masked language modeling (TMLM) and node order prediction (NOP) with a hybrid objective. TMLM uses a novel masking strategy designed according to the tree’s characteristics to help the model understand the AST and infer the missing semantics of the AST. With NOP, TreeBERT extracts the syntactical structure by learning the order constraints of nodes in AST. We pre-trained TreeBERT on datasets covering multiple programming languages. On code summarization and code documentation tasks, TreeBERT outperforms other pre-trained models and state-of-the-art models designed for these tasks. Furthermore, TreeBERT performs well when transferred to the pre-trained unseen programming language.

Details