5 papers
Physical Prompt Injection Attacks on Large Vision-Language Models
Chen Ling, Kai Hu, Hangcheng Liu +3
Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical environments. While LVLMs are known t…
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
AGI Team, Yuxuan Cai, Lu Chen +62
The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incent…
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
Yicheng Chen, Yining Li, Kai Hu +3
Data quality and diversity are key to the construction of effective instruction-tuning datasets. % With the increasing availability of open-source instruction-tuning datasets, it i…
M-LLM Based Video Frame Selection for Efficient Video Understanding
Kai Hu, Feng Gao, Xiaohan Nie +8
Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply n…
DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering
Haochen Wang, Kai Hu, Liangcai Gao
Remote work and online courses have become important methods of knowledge dissemination, leading to a large number of document-based instructional videos. Unlike traditional video…