Media
You'll never trust video again once you see what Sora 2 can do
Open AI's new video-generation app is both shocking and terrifying. The new technology can create an AI-generated video that can be up to a minute long.
Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
Our pipeline introduces three innovative components.
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization Qi Song
Multimodal contrastive learning (MCL) has recently demonstrated significant success across various tasks.
A Benchmark for Long-context Interleaved Video-Language Understanding Haoning Wu Dongxu Li Bei Chen Junnan Li Rhymes AI
Specifically, as part of the question, it contains a referring query that references related video contexts, called referred context .
GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
GPT can handle core motion comprehension and generation tasks, including text-to-motion, motion-to-text, music-to-dance, dance-to-music, motion prediction, and motion in-between.
Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing Siyi Chen
Recently, diffusion models have emerged as a powerful class of generative models. Despite their success, there is still limited understanding of their semantic spaces. This makes it challenging to achieve precise and disentangled image generation without additional training, especially in an unsupervised way.
