Publications (23)
RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
Jianing Guo, Zhenhong Wu, Chang Tu +13
In Vision-Language-Actionf(VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broad…
The Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos
Shuning Zhang, Zhaoxin Li, Changxi Wen +8
The proliferation of Vision-Language Models (VLMs) introduces profound privacy risks from personal videos. This paper addresses the critical yet unexplored inferential privacy thre…
Fiber Transmission Model with Parameterized Inputs based on GPT-PINN Neural Network
Yubin Zang, Boyu Hua, Zhipeng Lin +4
In this manuscript, a novelty principle driven fiber transmission model for short-distance transmission with parameterized inputs is put forward. By taking into the account of the…
Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li +13
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. Howev…
Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning
Xin Yu, Rongye Shi, Pu Feng +4
Incorporating symmetry as an inductive bias into multi-agent reinforcement learning (MARL) has led to improvements in generalization, data efficiency, and physical consistency. Whi…
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Zheng Yuwei +12
Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose failure causes worst-case system performance degradations.…
Position: Human-Robot Interaction in Embodied Intelligence Demands a Shift From Static Privacy Controls to Dynamic Learning
Shuning Zhang, Hong Jia, Simin Li +4
The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from amb…
SpikeMS: Deep Spiking Neural Network for Motion Segmentation
Chethan M. Parameshwara, Simin Li, Cornelia Fermüller +3
Spiking Neural Networks (SNN) are the so-called third generation of neural networks which attempt to more closely match the functioning of the biological brain. They inherently enc…
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Simin Li, Ruixiao Xu, Jingqiao Xiu +4
In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL m…
Principle Driven Parameterized Fiber Model based on GPT-PINN Neural Network
Yubin Zang, Boyu Hua, Zhenzhou Tang +5
In cater the need of Beyond 5G communications, large numbers of data driven artificial intelligence based fiber models has been put forward as to utilize artificial intelligence's…
The topological complexity of Cantor attractors for unimodal interval maps
Simin Li, Weixiao Shen
For a non-flat unimodal map with a Cantor attractor, we show that for any open cover of this attractor, the complexity function is of order $n…
AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
Tianbo Wang, Yuqing Ma, Kewei Liao +4
Large Vision-Language Models (LVLMs) have achieved substantial progress in cross-modal tasks. However, due to language bias, LVLMs are susceptible to object hallucination, which ca…
Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences
Shuning Zhang, Ying Ma, Jingruo Chen +3
The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model…
Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Jianing Guo, Fangzheng Chen, Zihao Mao +12
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside sim…
AI Deception: Risks, Dynamics, and Controls
Boyuan Chen, Sitong Fang, Jiaming Ji +56
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an…
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
Simin Li, Jun Guo, Jingqiao Xiu +8
This study probes the vulnerabilities of cooperative multi-agent reinforcement learning (c-MARL) under adversarial attacks, a critical determinant of c-MARL's worst-case performanc…
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
Simin Li, Jun Guo, Jingqiao Xiu +6
In this study, we explore the robustness of cooperative multi-agent reinforcement learning (c-MARL) against Byzantine failures, where any agent can enact arbitrary, worst-case acti…
Magnetization dynamics modulated by Dzyaloshinskii-Moriya interaction in the double-interface spin transfer torque magnetic tunnel junction
Simin Li, Zhaohao Wang, Yijie Wang +2
Currently double-interface MTJs have been developed for enhancing the thermal stability barrier in small technology node. Dzyaloshinskii-Moriya interaction (DMI) inevitably exists…
Bayesian Robust Financial Trading with Adversarial Synthetic Market Data
Haochong Xia, Simin Li, Ruixiao Xu +7
Algorithmic trading relies on machine learning models to make trading decisions. Despite strong in-sample performance, these models often degrade when confronted with evolving real…
Fiber neural networks for the intelligent optical fiber communications
Yubin Zang, Zuxing Zhang, Simin Li +2
Optical neural networks have long cast attention nowadays. Like other optical structured neural networks, fiber neural networks which utilize the mechanism of light transmission to…
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
Simin Li, Shuing Zhang, Gujun Chen +6
Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real…
Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning
Jun Guo, Yonghong Chen, Yihang Hao +3
While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversar…
Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection
Simin Li, Huangxinxin Xu, Jiakai Wang +4
Billions of people are sharing their daily life images on social media every day. However, their biometric information (e.g., fingerprint) could be easily stolen from these images.…