3 papers
cs.CV2026
PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining
Zelin Jia, Zhao Zhang, Zhicong Tang +2
Image-to-layer decomposition converts a flattened image into editable RGBA layers, enabling element-level editing in design workflows. Existing diffusion-based systems typically ad…
cs.CL2026
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
cs.CV2026
Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection
Jiangning Zhu, Bowen Li, Shenyu Qiao +4
Graphic designs, such as posters, advertisements, and infographics, are an important medium for communicating information and shaping understanding. Unlike natural images, they con…