7 papers
IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation
Yifan Li, Lichi Li, Anh Dao +15
While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks la…
Open Set Face Forgery Detection via Dual-Level Evidence Collection
Zhongyi Cai, Bryce Gernon, Wentao Bao +3
The surge in face forgeries has increasingly undermined confidence in the authenticity of online content. As generation algorithms rapidly evolve, new fake categories will constant…
Task-Aware Resolution Optimization for Visual Large Language Models
Weiqing Luo, Zhen Tan, Yifan Li +4
Real-world vision-language applications demand varying levels of perceptual granularity. However, most existing visual large language models (VLLMs), such as LLaVA, pre-assume a fi…
IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
Yifan Li, Yuhang Chen, Anh Dao +5
Existing Embodied Question Answering (EQA) benchmarks primarily focus on household environments, often overlooking safety-critical aspects and reasoning processes pertinent to indu…
Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations
Zhen Tan, Song Wang, Yifan Li +4
Post-hoc explanation methods provide interpretation by attributing predictions to input features. Natural explanations are expected to interpret how the inputs lead to the predicti…
Window Token Concatenation for Efficient Visual Large Language Models
Yifan Li, Wentao Bao, Botao Ye +4
To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sli…