王奕森

2026

大语言模型赋能的漏洞检测技术综述

《信息工程大学学报》

2026

基于Datalog逻辑推理与大模型语义增强的二进制数据结构重构方法

《软件导刊》

2026

CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer

2026

Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

International Conference on Learning Representations

DOI

2026

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

2026

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

arXiv.org

DOI

2026

BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification

arXiv.org

DOI

2026

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

Lecture notes in computer science

DOI

2025

DeepClap：一种基于残差对齐网络的漏洞跨模态搜索方法

《信息工程大学学报》

2025

保留因果关系的溯源图压缩方法

《网络与信息安全学报》

2025

$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning

Advances in Neural Information Processing Systems 38

DOI

2025

R^3-VQA: "Read the Room" by Video Social Reasoning

arXiv.org

DOI

2025

X-Guard: Multilingual Guard Agent for Content Moderation

arXiv.org

DOI

2025

SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning

arXiv.org

DOI

2024

嵌入式固件模糊测试研究综述

《小型微型计算机系统》

2024

A Canonicalization Perspective on Invariant and Equivariant Learning

Neural Information Processing Systems

DOI

2024

A Theoretical Understanding of Self-Correction through In-context Alignment

Neural Information Processing Systems

DOI

2024

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

Neural Information Processing Systems

DOI

2024

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs

arXiv.org

DOI

2024

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

Trans. Mach. Learn. Res.

DOI

2024

Meta Weighted Loss: Balanced Scene Graph Generation with Meta-Learning

Poster Volume Ⅰ The 2024 Twentieth International Conference on Intelligent Computing August 5-8, 2024 Tianjin, China

DOI

2024

How to Craft Backdoors with Unlabeled Data Alone?

arXiv.org

DOI

2024

What is Wrong with Perplexity for Long-context Language Modeling?

International Conference on Learning Representations

DOI

2024

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

International Conference on Learning Representations

DOI

2024

CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generation

arXiv.org

DOI

2023

CFA: Class-Wise Calibrated Fair Adversarial Training

Computer Vision and Pattern Recognition

DOI

2023

On the Generalization of Multi-modal Contrastive Learning

International Conference on Machine Learning

DOI

2023

Generalist: Decoupling Natural and Robust Generalization

Computer Vision and Pattern Recognition

DOI

2023

SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks

Neural Networks

DOI

2023

Rethinking Weak Supervision in Helping Contrastive Learning

International Conference on Machine Learning

DOI

2023

Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective

Neural Information Processing Systems

DOI

2023

On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2023

Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning

Neural Information Processing Systems

DOI

2023

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

Neural Information Processing Systems

DOI

2023

ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations

International Conference on Learning Representations

DOI

2023

A Message Passing Perspective on Learning Dynamics of Contrastive Learning

International Conference on Learning Representations

DOI

2023

W HAT C ONTRASTIVE L EARNING L EARNS B EYOND C LASS - WISE F EATURES ?

2023

Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks

IEEE International Conference on Computer Vision

DOI

2023

Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

International Conference on Learning Representations

DOI

2023

Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism

International Conference on Learning Representations

DOI

2023

Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States

International Conference on Learning Representations

2023

ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

International Conference on Learning Representations

DOI

2023

Equilibrium Image Denoising With Implicit Differentiation

IEEE Transactions on Image Processing

DOI

2023

Robust Long-Tailed Learning via Label-Aware Bounded CVaR

arXiv.org

DOI

2023

Towards Control-Centric Representations in Reinforcement Learning from Images

arXiv.org

DOI

2023

Appendix of Generalist: Decoupling Natural and Robust Generalization

2022

When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture

Neural Information Processing Systems

DOI

2022

Certified Adversarial Robustness Under the Bounded Support Set

International Conference on Machine Learning

2022

G2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters

International Conference on Machine Learning

2022

Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors

Neural Information Processing Systems

DOI

2022

Optimization-Induced Graph Implicit Nonlinear Diffusion

International Conference on Machine Learning

DOI

2022

How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders

Neural Information Processing Systems

DOI

2022

CerDEQ: Certifiable Deep Equilibrium Model

International Conference on Machine Learning

2022

Training much deeper spiking neural networks with a small number of time-steps

Neural Networks

DOI

2022

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation

Computer Vision and Pattern Recognition

DOI

2022

A Roadmap for Big Model

arXiv.org

DOI

2022

AggNCE: Asymptotically Identifiable Contrastive Learning

2022

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training

International Conference on Learning Representations

DOI

2022

Optimization inspired Multi-Branch Equilibrium Models

International Conference on Learning Representations

2022

GeoSegNet: point cloud semantic segmentation via geometric encoder–decoder modeling

The Visual Computer

DOI

2022

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

arXiv.org

DOI

2022

Variational Energy-Based Models: A Probabilistic Framework for Contrastive Self-Supervised Learning

2022

Efficient and Scalable Implicit Graph Neural Networks with Virtual Equilibrium

2022 IEEE International Conference on Big Data (Big Data)

DOI

2022

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

International Conference on Learning Representations

DOI

2022

Self-Ensemble Adversarial Training for Improved Robustness

International Conference on Learning Representations

DOI

2021

NeurIPS 2020观察与分析

《中国图象图形学报》

2021

On the Convergence and Robustness of Adversarial Training

International Conference on Machine Learning

2021

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Neural Information Processing Systems

2021

Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State

Neural Information Processing Systems

2021

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Neural Information Processing Systems

2021

Leveraged Weighted Loss for Partial Label Learning

International Conference on Machine Learning

2021

Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?

International Conference on Machine Learning

2021

Residual Relaxation for Multi-view Representation Learning

Neural Information Processing Systems

2021

On Training Implicit Models

Neural Information Processing Systems

2021

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Neural Information Processing Systems

2021

Gauge Equivariant Transformer

Neural Information Processing Systems

2021

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Neural Information Processing Systems

2021

GBHT: Gradient Boosting Histogram Transform for Density Estimation

International Conference on Machine Learning

2021

Adversarial Neuron Pruning Purifies Backdoored Deep Models

Neural Information Processing Systems

2021

Improving Gravitational Wave Detection with 2D Convolutional Neural Networks

International Conference on Pattern Recognition

DOI

2021

Efficient Equivariant Network

Neural Information Processing Systems

2021

Unlearnable Examples: Making Personal Data Unexploitable

International Conference on Learning Representations

2021

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

arXiv.org

2021

Generalization in Deep RL for TSP Problems via Equivariance and Local Search

SN Computer Science

DOI

2021

Game-theoretic Understanding of Adversarially Learned Features

arXiv.org

2021

Optimization Induced Equilibrium Networks

arXiv.org

2021

Moiré Attack (MA): A New Potential Risk of Screen Photos

arXiv.org

2021

Analysis and Applications of Class-wise Robustness in Adversarial Training

Knowledge Discovery and Data Mining

DOI

2021

Reparameterized Sampling for Generative Adversarial Networks

ECML/PKDD

DOI

2021

Fooling Adversarial Training with Inducing Noise

arXiv.org

2021

Improving Generalization of Deep Reinforcement Learning-based TSP Solvers

IEEE Symposium Series on Computational Intelligence

DOI

2021

Clustering Effect of (Linearized) Adversarial Robust Models

arXiv.org

2021

Demystifying Adversarial Training via A Unified Probabilistic Framework

2021

Improving Adversarial Robustness via Channel-wise Activation Suppressing

International Conference on Learning Representations

2021

Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions

arXiv.org

2020

Normalized Loss Functions for Deep Learning with Noisy Labels

International Conference on Machine Learning

2020

Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles

Computer Vision and Pattern Recognition

DOI

2020

Adversarial Weight Perturbation Helps Robust Generalization

Neural Information Processing Systems

2020

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

International Conference on Learning Representations

2020

Improving Adversarial Robustness Requires Revisiting Misclassified Examples

International Conference on Learning Representations

2020

Improving Query Efficiency of Black-box Adversarial Attack

European Conference on Computer Vision

DOI

2020

A Unified Approach to Interpreting and Boosting Adversarial Transferability

International Conference on Learning Representations

2020

Temporal Calibrated Regularization for Robust Noisy Label Learning

IEEE International Joint Conference on Neural Network

DOI

2019

基于最大局部密度间隔的特征选择方法

《计算机工程与设计》

DOI

2019

基于最大平均间隔的特征选择方法研究

《信息工程大学学报》

2019

Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems

Pattern Recognition

DOI

2019

Hilbert-Based Generative Defense for Adversarial Examples

IEEE International Conference on Computer Vision

DOI

2019

Collaborative Representation Cascade for Single-Image Super-Resolution

IEEE Transactions on Systems, Man, and Cybernetics: Systems

DOI

2019

Symmetric Cross Entropy for Robust Learning With Noisy Labels

IEEE International Conference on Computer Vision

DOI

2019

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation

Conference on Empirical Methods in Natural Language Processing

DOI

2019

Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation

arXiv.org

2019

Self-Attentive Networks for one-shot Image Recognition

IEEE International Conference on Multimedia and Expo

DOI

2018

面向网络打印机的脆弱性分析

《计算机应用与软件》

2018

集成学习之随机森林算法综述

《信息通信技术》

2018

A Novel Consistent Random Forest Framework: Bernoulli Random Forests

IEEE Transactions on Neural Networks and Learning Systems

DOI

2018

Iterative Learning with Open-set Noisy Labels

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

DOI

2018

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data

Conference on Uncertainty in Artificial Intelligence

2018

Dimensionality-Driven Learning with Noisy Labels

International Conference on Machine Learning

2018

Decoupled Networks

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

DOI

2018

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

International Conference on Learning Representations

2017

Robust Survey Aggregation with Student-t Distribution and Sparse Representation

International Joint Conference on Artificial Intelligence

DOI

2017

Unbiased Multivariate Correlation Analysis

AAAI Conference on Artificial Intelligence

DOI

2017

Student-t Process Regression with Student-t Likelihood

International Joint Conference on Artificial Intelligence

DOI

2017

A generic denoising framework via guided principal component analysis

Journal of Visual Communication and Image Representation

DOI

2017

Unifying attribute splitting criteria of decision trees by Tsallis entropy

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2017

決定木分類のためのより少ない欲張り2項Tsallisエントロピー情報計量アプローチ【Powered by NICT】

2017

A less-greedy two-term Tsallis Entropy Information Metric approach for decision tree classification

Knowledge-Based Systems

DOI

2017

Link sign prediction by Variational Bayesian Probabilistic Matrix Factorization with Student-t Prior

Information Sciences

DOI

2017

Residual Convolutional CTC Networks for Automatic Speech Recognition

arXiv.org

2016

基于ARMv8架构gadget自动搜索框架

《计算机应用与软件》

2016

基于指令集随机化的代码注入型攻击防御技术

《计算机应用与软件》

2016

Bernoulli Random Forests: Closing the Gap between Theoretical Consistency and Empirical Soundness

International Joint Conference on Artificial Intelligence

2016

Student-t Process Regression with Dependent Student-t Noise

European Conference on Artificial Intelligence

DOI

2016

Improving decision trees by Tsallis Entropy Information Metric method

IEEE International Joint Conference on Neural Network

DOI

2016

A novel feature subspace selection method in random forests for high dimensional data

IEEE International Joint Conference on Neural Network

DOI

2016

Unifying the Split Criteria of Decision Trees Using Tsallis Entropy

2015

Unifying Decision Trees Split Criteria Using Tsallis Entropy

2020

Adversarial Weight Perturbation Helps Robust Generalization

neural information processing systems