9 papers
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Qi Li, Bo Yin, Weiqi Huang +6
Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied na…
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Lexiang Xiong, Qi Li, Jingwen Ye +1
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this…
Reinforced Model Merging
Jiaqi Han, Jingwen Ye, Shunyu Liu +4
The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the pa…
Adversarial Training: A Survey
Mengnan Zhao, Lihe Zhang, Jingwen Ye +3
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the…
Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching
Ruonan Yu, Songhua Liu, Jingwen Ye +1
Dataset distillation or condensation refers to compressing a large-scale dataset into a much smaller one, enabling models trained on this synthetic dataset to generalize effectivel…
Heavy Labels Out! Dataset Distillation with Label Space Lightening
Ruonan Yu, Songhua Liu, Zigeng Chen +2
Dataset distillation or condensation aims to condense a large-scale training dataset into a much smaller synthetic one such that the training performance of distilled and original…