3 papers
cs.CV2026
EventFlash: Towards Efficient MLLMs for Event-Based Vision
Shaoyu Liu, Jianing Li, Guanghui Zhao +4
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, curre…
cs.CV2025
LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration
Wen Jiang, Li Wang, Kangyao Huang +6
Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in viewpoint, and dynamic s…
cs.CV2025
CETUS: Causal Event-Driven Temporal Modeling With Unified Variable-Rate Scheduling
Hanfang Liang, Bing Wang, Shizhen Zhang +4
Event cameras capture asynchronous pixel-level brightness changes with microsecond temporal resolution, offering unique advantages for high-speed vision tasks. Existing methods oft…