IEEE

Self-Attention-Based Text Encoder for Enhancing DMGAN Text-to-Image Generation

Abstract: Generating images that align with textual input using text-to-image (TTI) generation models is a challenging task. Generative adversarial network (GAN) based TTI models can produce realistic ...
GitHub

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance. Notably, ...
New York Post

Why CNN staffers should be careful what they wish for in Warner’s Netflix merger

The word inside CNN is that staffers are thrilled that their parent, Warner Bros. Discovery, agreed to merge with Netflix instead of Paramount Skydance. They fear the latter’s Trump-friendly owners, ...
IEEE

Light CNN-Transformer Dual-Branch Network for Real-Time Semantic Segmentation

Abstract: Convolutional Neural Networks (CNN) have widely used in semantic segmentation, and can effectively extract local hierarchical information while being unsatisfactory in extracting global ...