Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding
Weili Xu, Enxin Song, Wenhao Chai +3
The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs…
cs.CV2025
An Empirical Study of GPT-4o Image Generation Capabilities
Sixiang Chen, Jinbin Bai, Zhuoran Zhao +16
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to brid…
cs.CV2024
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
Yunlong Lin, Tian Ye, Sixiang Chen +6
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limit…