Country

Apple AI Researchers Develop GMPIs (Generative Multiplane Images) For Making A 2D GAN 3D-Aware

Using a given training dataset as a guide, generative adversarial networks (GANs) have achieved excellent results when sampling new pictures that are "similar" to...

Top Artificial Intelligence (AI) Chip Companies Leading The Way (2023)

Future economic growth could be significantly impacted by AI chips, which will unavoidably be used in robotics, smart homes where electronic items are becoming...

Stanford Researcher develops a simple prompting strategy that enables open-source LLMs with 30x fewer parameters to exceed the few-shot performance of GPT3-175B

By improving the in-context learning quality of smaller and open source models, more researchers and organizations can study and apply the technology. One exciting...

Researchers from MIT Propose an AI Model that Knows How to Generate Line Drawings from Photographs

If you have ever seen an artist working on a drawing, you probably noticed they start with the line drawing. They draw the outlines...

A New AI Framework Called Text2Poster Automatically Generates Visually-Effective Posters From The Textual Information

Posters have been widely utilized in numerous commercial and nonprofit contexts to promote and disseminate information as a type of media with artistic and...

RecolorNeRF: A Novel User-Friendly Color Editing Approach For The Neural Radiance Field

Neural radiance fields (NeRF) are a potent representation of 3D scenes, making it possible that they may one day replace photos and movies as...

Meet HyDE: An Effective Fully Zero-Shot Dense Retrieval Systems That Require No Relevance Supervision, Works Out-of-Box, And Generalize Across Tasks

Dense retrieval, a technique for finding documents based on similarities in semantic embedding, has been shown effective for tasks including fact-checking, question-answering, and online...

Meet GLIGEN: An AI Approach that Extends the Functionality of Existing Pre-Trained Text-to-Image Diffusion Models by Enabling Conditioning on Grounding Inputs

Since millions of image-text pairings have been used to train diffusion models, it only makes sense to ask if they can add additional conditional...

Top Artificial Intelligence-Based Startups in Japan

Machines that have been taught to understand and learn similarly to humans are said to have artificial intelligence (AI). They can be introduced to...

Top Innovative Artificial Intelligence (AI) Powered Startups Based in Singapore

Artificial intelligence is the ability of machines, especially computer systems, to mimic human intellectual capabilities. Some examples of particular AI applications include expert systems,...

Google Brain and Tel Aviv University Researchers Proposed A Text-To-Image Model Guided By Sketches

Large text-to-image diffusion models have been an innovative tool for creating and editing content because they make it possible to synthesize a variety of...

Researchers From China Introduce DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching

Several popular geometric computer vision systems rely on local feature matching to function, such as Simultaneous Localization and Mapping (SLAM) and Structure-from-Motion (SFM). Detector-based...

Recent articles

Check Out Our Super Cool AI Research Newsletter While It's Still Free

X