TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

Yichuan Mo, Hui Huang, Mingjie Li +2

GBHT: Gradient Boosting Histogram Transform for Density Estimation

Jingyi Cui, Hanyuan Hang, Yisen Wang +1

Diagnosing Visual Ignorance in Vision-Language Models

Runyu Zhou, Qi Zhang, Qixun Wang +1

On the Convergence and Robustness of Adversarial Training

Yisen Wang, Xingjun Ma, James Bailey +3

Normalized Loss Functions for Deep Learning with Noisy Labels

Xingjun Ma, Hanxun Huang, Yisen Wang +3

Three-dimensional signal processing: a new approach in dynamical sampling via tensor products

Yisen Wang, Hanqin Cai, Longxiu Huang

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

Yifei Wang, Qi Zhang, Yisen Wang +2

$q$-Breathers in the diatomic $β$-Fermi-Pasta-Ulam- Tsingou chains

Lin Deng, Hang Yu, Zhigang Zhu +3

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training

Yisen Wang, Yichuan Mo, Hongjun Wang +2

Reparameterized Sampling for Generative Adversarial Networks

Yifei Wang, Yisen Wang, Jiansheng Yang +1

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks

Hanxun Huang, Yisen Wang, Sarah Monazam Erfani +3

Impact of on-site potentials on $q$-breathers in nonlinear chains

Lin Deng, Chengguan Fang, Hang Yu +5

On the Generalization of Multi-modal Contrastive Learning

Qi Zhang, Yifei Wang, Yisen Wang

Advancing LLM Safe Alignment with Safety Representation Ranking

Tianqi Du, Zeming Wei, Quan Chen +2

On Training Implicit Models

Zhengyang Geng, Xin-Yu Zhang, Shaojie Bai +2

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

Xiaojun Guo, Runyu Zhou, Yifei Wang +8

Improving Query Efficiency of Black-box Adversarial Attack

Yang Bai, Yuyuan Zeng, Yong Jiang +3

Adversarial Neuron Pruning Purifies Backdoored Deep Models

Dongxian Wu, Yisen Wang

An Augmentation Overlap Theory of Contrastive Learning

Qi Zhang, Yifei Wang, Yisen Wang

How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders

Qi Zhang, Yifei Wang, Yisen Wang

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

Lixing Niu, Jiapeng Li, Xingping Yu +6

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

Qirui Mi, Zhijian Ma, Mengyue Yang +4

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

Yichuan Mo, Yuji Wang, Zeming Wei +1

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

Yichuan Mo, Dongxian Wu, Yifei Wang +2

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

Dong-Dong Chen, Yisen Wang, Jinfeng Yi +2

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data

Yisen Wang, Bo Dai, Lingkai Kong +3

Parallel BiLSTM-Transformer networks for forecasting chaotic dynamics

Junwen Ma, Mingyu Ge, Yisen Wang +2

Analysis and Applications of Class-wise Robustness in Adversarial Training

Qi Tian, Kun Kuang, Kelu Jiang +2

DWM: Separating World Effects from Actions in Latent World Models

Yi-Ge Zhang, Tianqi Du, Qi Zhang +1

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

Yifei Wang, Yuyang Wu, Zeming Wei +2

CFA: Class-wise Calibrated Fair Adversarial Training

Zeming Wei, Yifei Wang, Yiwen Guo +1

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

Yisen Wang, Yao Teng, Limin Wang

Symmetry Hierarchy and Thermalization Frustration in Graphene Nanoresonators

Yisen Wang, Liang Huang

Do Generated Data Always Help Contrastive Learning?

Yifei Wang, Jizhe Zhang, Yisen Wang

Fooling Adversarial Training with Inducing Noise

Zhirui Wang, Yifei Wang, Yisen Wang

Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Yifei Wang, Yisen Wang, Jiansheng Yang +1

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

Zhijian Zhuo, Yifei Wang, Jinwen Ma +1

Improving Generalization of Deep Reinforcement Learning-based TSP Solvers

Wenbin Ouyang, Yisen Wang, Shaochen Han +2

Identifying and Understanding Cross-Class Features in Adversarial Training

Zeming Wei, Yiwen Guo, Yisen Wang

Autoregressive Models Rival Diffusion Models at ANY-ORDER Generation

Tianqi Du, Lizhe Fang, Weijie Yang +4

On the Role of Discrete Tokenization in Visual Representation Learning

Tianqi Du, Yifei Wang, Yisen Wang

Long-Short Alignment for Effective Long-Context Modeling in LLMs

Tianqi Du, Haotian Huang, Yifei Wang +1

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

Yichuan Mo, Yukun Jiang, Yanbo Shi +4

On the Adversarial Transferability of Generalized "Skip Connections"

Yisen Wang, Yichuan Mo, Dongxian Wu +3

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

Dinghuai Zhang, Kartik Ahuja, Yilun Xu +2

Temporal Calibrated Regularization for Robust Noisy Label Learning

Dongxian Wu, Yisen Wang, Zhuobin Zheng +1

When More is Less: Understanding Chain-of-Thought Length in LLMs

Yuyang Wu, Yifei Wang, Ziyu Ye +3

Dissecting the Failure of Invariant Learning on Graphs

Qixun Wang, Yifei Wang, Yisen Wang +1

Non-minimality of minimal telescopers explained by residues

Shaoshi Chen, Manuel Kauers, Christoph Koutschan +3

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

Yifei Wang, Liangchen Li, Jiansheng Yang +2

Monet: Reasoning in Latent Visual Space Beyond Images and Language

Qixun Wang, Yang Shi, Yifei Wang +5

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

Ranjie Duan, Xingjun Ma, Yisen Wang +3

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

Ang Li, Zhihang Yuan, Yang Zhang +2

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

Mingqing Xiao, Qingyan Meng, Zongpeng Zhang +2

Non-negative Contrastive Learning

Yifei Wang, Qi Zhang, Yaoyu Guo +1

A Roadmap for Big Model

Sha Yuan, Hanyu Zhao, Shuai Zhao +97

Incorporating Arbitrary Matrix Group Equivariance into KANs

Lexiang Hu, Yisen Wang, Zhouchen Lin

Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning

Tianqi Du, Qi Zhang, Yifei Wang +1

Generalist: Decoupling Natural and Robust Generalization

Hongjun Wang, Yisen Wang

An Augmentation-Aware Theory for Self-Supervised Contrastive Learning

Jingyi Cui, Hongwei Wen, Yisen Wang

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Ang Li, Yichuan Mo, Mingjie Li +1

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

Qingyan Meng, Mingqing Xiao, Shen Yan +3

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

Chen Ma, Xiangyu Guo, Li Chen +2

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Zeming Wei, Yifei Wang, Ang Li +2

Emergence of Gamma-Type Upward-Phase Statistics in the Collatz Map: An Effective Poisson Process Mechanism

Weicheng Fu, Xiaobin Liu, Yisen Wang

Rethinking Personalization in Large Language Models at the Token Level

Chenheng Zhang, Yijun Lu, Lizhe Fang +7

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

Lizhe Fang, Yifei Wang, Zhaoyang Liu +5

Optimization Induced Equilibrium Networks

Xingyu Xie, Qiuhao Wang, Zenan Ling +4

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

Wenbin Ouyang, Yisen Wang, Paul Weng +1

Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

Ze Peng, Jian Zhang, Yisen Wang +3

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

Jiangyan Ma, Yifei Wang, Yisen Wang

A Unified Approach to Interpreting and Boosting Adversarial Transferability

Xin Wang, Jie Ren, Shuyun Lin +3

Towards provable probabilistic safety for scalable embodied AI systems

Linxuan He, Lingxiang Fan, Qing-Shan Jia +13

From Near-Integrable to Far-from-Integrable: A Unified Picture of Thermalization and Heat Transport

Weicheng Fu, Zhen Wang, Yisen Wang +2

Adversarial Examples Are Not Real Features

Ang Li, Yifei Wang, Yiwen Guo +1

On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy

Jingyi Cui, Qi Zhang, Yifei Wang +1

Rethinking Invariance in In-context Learning

Lizhe Fang, Yifei Wang, Khashayar Gatmiry +2

MADE: Graph Backdoor Defense with Masked Unlearning

Xiao Lin, Mingjie Li, Yisen Wang

Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

Ang Li, Yichuan Mo, Mingjie Li +2

The Structure of the Route to the Period-three Orbit in the Collatz Map

Weicheng Fu, Yisen Wang

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

Taiye Chen, Zeming Wei, Ang Li +1

Understanding the Role of Equivariance in Self-supervised Learning

Yifei Wang, Kaiwen Hu, Sharut Gupta +3

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

Shihao Zhao, Xingjun Ma, Yisen Wang +3

Identifiable Contrastive Learning with Automatic Feature Importance Discovery

Qi Zhang, Yifei Wang, Yisen Wang

Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems

Xingjun Ma, Yuhao Niu, Lin Gu +4

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima

Yiming Tang, Harshvardhan Saini, Zhaoqian Yao +6

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

Yifei Wang, Yisen Wang, Jiansheng Yang +1

S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localization

Chenghao Zhang, Lun Luo, Si-Yuan Cao +6

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

Qingyan Meng, Mingqing Xiao, Shen Yan +3

On the Summability Problem of Multivariate Rational Functions in the Mixed Case

Shaoshi Chen, Lixin Du, Hanqian Fang +1

Nonintegrability-driven Transition from Kinetics to Hydrodynamics

Weicheng Fu, Zhen Wang, Yisen Wang +2

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

Quanshi Zhang, Xin Wang, Jie Ren +4

ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

Xiaojun Guo, Yifei Wang, Tianqi Du +1

Mitigating Compounding Error via Video Representation Regularization

Taiye Chen, Qi Zhang, Yisen Wang

The paper studies why autoregressive video generation models accumulate errors over time and introduces a lightweight regularization that stabilizes hidden representations, reducin…

GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling

Chen Chen, Yisen Wang, Honghua Chen +6

A Generalization Theory for JEPA-Based World Models

Jingyi Cui, Qi Zhang, Hongwei Wen +1

Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions

Nodens Koren, Qiuhong Ke, Yisen Wang +2

Symbolic Integration of Differential Forms: From Abel to Zeilberger

Shaoshi Chen, David A. Cox, Yisen Wang

Self-Ensemble Adversarial Training for Improved Robustness

Hongjun Wang, Yisen Wang

How to generate all possible rational Wilf-Zeilberger forms?

Shaoshi Chen, Christoph Koutschan, Yisen Wang