8 papers
V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
Jiazhou Zhou, Yucheng Chen, Hongyang Li +4
Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability aris…
T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection
Jiazhou Zhou, Qing Jiang, Kanghao Chen +4
Object detection methods have evolved from closed-set to open-set paradigms over the years. Current open-set object detectors, however, remain constrained by their exclusive relian…
PASS: Path-selective State Space Model for Event-based Recognition
Jiazhou Zhou, Kanghao Chen, Lei Zhang +1
Event cameras are bio-inspired sensors that capture intensity changes asynchronously with distinct advantages, such as high temporal resolution. Existing methods for event-based ob…
MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection
Xu Zheng, Yuanhuiyi Lyu, Lutao Jiang +3
In this paper, we address the challenging modality-agnostic semantic segmentation (MaSS), aiming at centering the value of every modality at every feature granularity. Training wit…
Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation
Xu Zheng, Yuanhuiyi Lyu, Jiazhou Zhou +1
Fusing an arbitrary number of modalities is vital for achieving robust multi-modal fusion of semantic segmentation yet remains less explored to date. Recent endeavors regard RGB mo…
EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding
Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu +1
In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the…