September 2026

Current neural image compression (NIC) methods primarily focus on signal fidelity optimization. While perceptually optimized codecs can generate decoded images that better align with human visual pref

Vision-language object detectors (VLODs) pretrained on large image-text corpora exhibit strong zero-shot detection abilities, yet their performance often degrades on specialized downstream tasks that

Recent advances in pre-trained vision-language models have demonstrated remarkable zero-shot generalization capabilities. To further enhance these models’ adaptability to various downstream tasks, pro

As a distributed machine learning paradigm, federated learning enables collaborative training among multiple clients while preserving data privacy. However, in practical applications, it faces the cha

Predicting the physical properties of reconstructed 3D assets is essential for virtual reality interactions. However, current systems often depend on manually assigning properties such as stiffness an

While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Cata

Few-shot semantic segmentation has attracted growing interest for its ability to generalize to novel object categories using only a few annotated samples. To address data scarcity, recent methods inco

Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception tasks and the development of end-to-end autonomous driving systems. How

Text-rich scene image super-resolution (TS-ISR) aims to recover high-quality images with legible text from degraded inputs, benefiting mobile photography and enhancing visual inputs for multimodal und

Diffusion models have shown promising results in free-form inpainting. Recent studies based on refined diffusion samplers or novel architectural designs have produced realistic results with improved c