5 papers
Constrained Differentiable Policy Learning for Safe Quadrotor Navigation
Yan Rui Tan, Praveen Krishnapur, Zeyu Feng +3
Differentiable simulation enables efficient policy optimization through analytic gradients, yet safety is commonly incorporated as a weighted penalty, requiring manual tuning of th…
Evolutionary Computation for Trustworthy AI: From Attacks and Defenses to Self-Evolving Era
Junhao Dong, Chenkai Wang, Xuanhui Lin +8
As Artificial Intelligence (AI) has evolved from task-specific models to foundation models and agents, the scope of trustworthy AI has expanded from model-level robustness to the r…
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
Qi Rong Sua, Junhao Dong, Nguyen Duc Thai +3
Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We…
Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain
Daizong Liu, Junhao Dong, Zhiyuan Ma +6
Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information, showing remarkable progress…
Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs
Tianyi Tang, Zhuoyi Lin, Zeyu Feng +4
Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical rea…