Research team debuts the first visual pre-training paradigm tailored for CTR prediction, lifting Taobao GMV by 0.88% (p < ...

According to @SciTechera, a new AI training approach applies next-token prediction—commonly used in language models—to Vision AI by treating visual embeddings as sequential tokens. This method for ...

Existing zero-shot temporal action detection (ZS-TAD) methods predominantly use fully supervised or unsuper- vised strategies to recognize unseen activities. However, these training-based methods are ...

Large vision-language models are improving at describing images, yet hallucinations still erode trust by introducing contradictions and fabricated details that limit practical applications. In ...

Abstract: Vision-Language Pre-training (VLP) models exhibit pronounced vulnerability to multimodal adversarial examples, necessitating rigorous robustness research, particularly for transferable ...

Abstract: The integration of visual and textual data in Vision- Language Pre-training (VLP) models is crucial forenhancing vision-language understanding. However, the adversarial robustness of these ...

Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this ...

Bruce Hansen, professor of psychology and neuroscience at Colgate, and Michelle Greene, assistant professor of psychology at Barnard College, recently received a three-year award from the National ...

Researchers at Nvidia have developed a new technique that flips the script on how large language models (LLMs) learn to reason. The method, called reinforcement learning pre-training (RLP), integrates ...

What if a robot could not only see and understand the world around it but also respond to your commands with the precision and adaptability of a human? Imagine instructing a humanoid robot to “set the ...

Contrastive Language-Image Pre-training (CLIP) has become important for modern vision and multimodal models, enabling applications such as zero-shot image classification and serving as vision encoders ...