6 papers
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
Hao Wang, Yiqun Sun, Pengfei Wei +2
Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety…
Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models
Issa Sugiura, Keito Sasagawa, Keisuke Nakao +8
Developing vision-language models (VLMs) that generalize across diverse tasks requires large-scale training datasets with diverse content. In English, such datasets are typically c…
VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction
Hao Wang, Eiki Murata, Lingfang Zhang +11
Recent advances in multimodal large language models (MLLMs) have significantly enhanced video understanding capabilities, opening new possibilities for practical applications. Yet…
Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
Hao Wang, Pinzhi Huang, Jihan Yang +2
The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages…
Harmony: A Human-Aware, Responsive, Modular Assistant with a Locally Deployed Large Language Model
Ziqi Yin, Mingxin Zhang, Daisuke Kawahara
Large Language Models (LLMs) offer powerful capabilities for natural language understanding, enabling more intelligent smart home assistants. However, existing systems often rely o…
Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance
Ziqi Yin, Hao Wang, Kaito Horio +2
We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs). Polite language in human communications often garners more compliance…