Publications (12)
Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks
Runqi Lin
With deep neural networks (DNNs) increasingly embedded in modern society, ensuring their safety has become a critical and urgent issue. In response, substantial efforts have been d…
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
Runqi Lin, Chaojian Yu, Bo Han +2
Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulner…
Instance-dependent Early Stopping
Suqin Yuan, Runqi Lin, Lei Feng +2
In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the training process when the model's performance…
AnisoLift: Anisotropic Latent Representations for Coarse Particle Liquid Enhancement
Zhengqing Gao, Huaxi Huang, Runqi Lin +6
Particle-based liquid simulation is widely used in graphics and physical modeling, but high-resolution rollouts remain computationally expensive. Consequently, many methods aim to…
FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
Runqi Lin, Alasdair Paren, Suqin Yuan +4
The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual…
PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
Ziwen Li, Xin Wang, Hanlue Zhang +8
The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs…
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
Runqi Lin, Chaojian Yu, Bo Han +1
Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address…
Mobile-VTON: High-Fidelity On-Device Virtual Try-On
Zhenchen Wan, Ce Chen, Runqi Lin +5
Virtual try-on (VTON) has recently achieved impressive visual fidelity, but most existing systems require uploading personal photos to cloud-based GPUs, raising privacy concerns an…
Understanding and Enhancing the Transferability of Jailbreaking Attacks
Runqi Lin, Bo Han, Fengwang Li +1
Jailbreaking attacks can effectively manipulate open-source large language models (LLMs) to produce harmful responses. However, these attacks exhibit limited transferability, faili…
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Runqi Lin, Chaojian Yu, Tongliang Liu
Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenom…
Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments
Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel +22
As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchma…
Mirage2Matter: A Physically Grounded Gaussian World Model from Video
Zhengqing Gao, Ziwen Li, Xin Wang +12
The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, ex…