9 papers
BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation
Chengcai Gao, Zhihong Sun, Xiaochuan Shi +2
The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic analysis or voting, face a trade-off b…
Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
Jiaqing Li, Yajuan Lu, Xiaochuan Shi +3
Vision-Language Models (VLMs) have achieved remarkable success, yet their reliance on massive datasets and unintended memorization of training data raise significant data security…
General Humanoid Whole-Body Control via Pretraining and Fast Adaptation
Zepeng Wang, Jiangxing Wang, Shiqing Yao +8
Learning a general whole-body controller for humanoid robots remains challenging due to the diversity of motion distributions, the difficulty of fast adaptation, and the need for r…
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…
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Pengxiang Li, Zechen Hu, Zirui Shang +15
Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL):…
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…