Publications (4)
: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model
Zepeng Wang, Chao Ma, Linjiang Zhou +4
Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods main…
Axiomatization of Gradient Smoothing in Neural Networks
Linjiang Zhou, Xiaochuan Shi, Chao Ma +1
Gradients play a pivotal role in neural networks explanation. The inherent high dimensionality and structural complexity of neural networks result in the original gradients contain…
AdaptGrad: Adaptive Sampling to Reduce Noise
Linjiang Zhou, Chao Ma, Zepeng Wang +2
Gradient Smoothing is an efficient approach to reducing noise in gradient-based model explanation method. SmoothGrad adds Gaussian noise to mitigate much of these noise. However, t…
MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation
Shuaiye Lu, Linjiang Zhou, Xiaochuan Shi
Hallucinations in large vision-language models (LVLMs) often stem from the model's sensitivity to image tokens during decoding, as evidenced by attention peaks observed when genera…