9 papers
HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models
Jiajun Wu, Haoyu Kang, Yining Sun +13
Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing harmful-video benchmarks. Howeve…
VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Yining Sun, Haoyu Kang, Jiajun Wu +7
Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as…
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin +53
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally c…
47B Mixture-of-Experts Beats 671B Dense Models on Chinese Medical Examinations
Chiung-Yi Tseng, Danyang Zhang, Tianyang Wang +8
The rapid advancement of large language models(LLMs) has prompted significant interest in their potential applications in medical domains. This paper presents a comprehensive bench…
Mixture of Experts in Large Language Models
Danyang Zhang, Junhao Song, Ziqian Bi +5
This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performanc…
Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing Dialogue
Lin Yu, Xiaofei Han, Yifei Kang +4
Recent advances in large language models (LLMs) have enabled fluent dialogue systems, but most remain reactive and struggle in emotionally rich, goal-oriented settings such as mark…