8 papers
Visual Token Compression Enhances Robustness of MLLMs
Shishen Gu, Jiequan Cui, Wenbo Hu +3
In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbrea…
Deep sub-ensembles meets quantile regression: uncertainty-aware imputation for time series
Ying Liu, Peng Cui, Wenbo Hu +1
Real-world time series data often exhibits substantial missing values, posing challenges for advanced analysis. A common approach to addressing this issue is imputation, where the…
Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding
Youze Wang, Zijun Chen, Ruoyu Chen +8
Recent advancements in multimodal large language models for video understanding (videoLLMs) have enhanced their capacity to process complex spatiotemporal data. However, challenges…
Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning
Zijun Chen, Wenbo Hu, Richang Hong
Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However,…
Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts
Xinlei Xiong, Wenbo Hu, Shuxun Zhou +5
Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere, necessitating probabilistic approaches to quantify uncertainty. While traditional ensemble…
Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Youze Wang, Wenbo Hu, Yinpeng Dong +3
Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other type…