Indie GAN Interpolation Method Turns Selfies into Cartoon Characters

Pinkney and Adler NeurIPS 2020 workshop paper enables realistic image generation in domains such as animation and ukiyo-e with creative control on the output. | Continue reading


@syncedreview.com | 4 years ago

ICLR 2021 Submission: Deeper VAEs Excel on Natural Image Benchmarks

ICLR 2021 submitted paper proposes efficient VAEs that outperform PixelCNN-based autoregressive models in log-likelihood on natural image benchmarks. | Continue reading


@syncedreview.com | 4 years ago

‘Farewell Convolutions’ – ML Community Applauds Anonymous ICLR 2021 Paper

ICLR 2021 paper An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale suggests Transformers can outperform top CNNs on CV at scale. | Continue reading


@syncedreview.com | 4 years ago

PwC-Powered Code Tab Added to ArXiv ML Papers

PwC and arXiv jointly announced their partnership yesterday, unveiling a convenient new Code tab on the abstract page of arXiv Machine Learning articles. | Continue reading


@syncedreview.com | 4 years ago

Neuron-Mimicking Nanoscale Electronic Circuit Element for Neuromorphic AI

Researchers introduce an isolated nanoscale electronic circuit element that can perform nonmonotonic operations and transistorless all-analogue computations. | Continue reading


@syncedreview.com | 4 years ago

Google AI Helps Sign Language ‘Take the Floor’ in Video Conferences

Google AI researchers developed a sign language detection model for video conferencing applications that can perform real-time identification of a person signing as an active speaker. | Continue reading


@syncedreview.com | 4 years ago

Google, Cambridge, DeepMind's ‘Performer’ Transformer Slashes Compute Costs

A team from Google, University of Cambridge, DeepMind, and Alan Turing Institute have proposed a new type of Transformer dubbed Performer, based on a Fast Attention Via positive Orthogonal Random f… | Continue reading


@syncedreview.com | 4 years ago

PyTorch / XLA Library Reaches General Availability on Google Cloud

It was announced yesterday in a PyTorch blog post that the PyTorch / XLA library, a package that enables PyTorch to connect to Google TPUs and use TPU cores as devices, is now generally available o… | Continue reading


@syncedreview.com | 4 years ago

Facebook’s Dynabench ‘Radically Rethinks AI Benchmarking’

Facebook researchers introduced a new research platform for dynamic data collection and benchmarking called Dynabench, which will offer a more accurate and sustainable way for evaluating progress i… | Continue reading


@syncedreview.com | 4 years ago

Nvidia Releases ‘Imaginaire’ Library for Image and Video Synthesis

Imaginaire, a universal PyTorch library designed for various GAN-based tasks and methods. | Continue reading


@syncedreview.com | 4 years ago

Facebook’s Flexible ‘Rag’ Language Model Achieves SOTA Results on Open-Domain QA

Researchers introduced retrieval-augmented generation - a hybrid, end-to-end differentiable model that combines an information retrieval component with a seq2seq generator. | Continue reading


@syncedreview.com | 4 years ago

Facebook AI Wav2Vec 2.0: Automatic Speech Recognition from 10 Minute Sample

Facebook AI researchers have open-sourced the new wav2vec 2.0 algorithm for self-supervised language learning. | Continue reading


@syncedreview.com | 4 years ago

Google Approaches Bert-Level Performance Using 300x Fewer Parameters

The trimmed-down pQRNN extension to Google AI’s projection attention neural network PRADO compares to BERT on text classification tasks for on-device use. | Continue reading


@syncedreview.com | 4 years ago

Facebook Reality Labs: ‘Tools That Help People Feel Connected’

VR and AR will converge to combine the real and virtual, as Facebook Reality Labs researchers, developers, and engineers aim to change how we see the world. | Continue reading


@syncedreview.com | 4 years ago

Tracking Recent Topics and Trends in 3D Photo Generation

Synced has identified a few significant technical advancements in the 3D photo field that we believe may be of interest to our readers. | Continue reading


@syncedreview.com | 4 years ago

New Google and Oxford Model Time-Shifts People in Videos

A group of researchers from Google Research and the University of Oxford have introduced a novel technique that can “retiming” people’s movements in videos. | Continue reading


@syncedreview.com | 4 years ago

After 15 Long Years, a NumPy Paper Finally Appears

NumPy is the foundation upon which the scientific Python ecosystem is constructed. | Continue reading


@syncedreview.com | 4 years ago

DeepMind Approach ‘Bootstraps’ Self-Supervised Learning of Image Representations

From an augmented view of an image, the researchers trained the online network to predict the target network representation of the same image under a different augmented view. | Continue reading


@syncedreview.com | 4 years ago

Czech Tech Does the Monster Mash: Animating 3D Models in Seconds

Monster Mash, a novel AI-powered 3D modelling and animation tool, aims to make these arduous 3D animation processes a whole lot easier. | Continue reading


@syncedreview.com | 4 years ago

Microsoft Democratizes DeepSpeed with Four New Technologies

Microsoft has released four additional DeepSpeed technologies to enable even faster training times, whether on supercomputers or a single GPU. | Continue reading


@syncedreview.com | 4 years ago

Ex-Uber AI Chief Scientist Zoubin Ghahramani Joins Google Brain Leadership Team

Former Uber Chief Scientist and VP for AI Zoubin Ghahramani has joined Google Research as part of the Google Brain team leadership. | Continue reading


@syncedreview.com | 4 years ago

Argo AI Model Jointly Plots Vehicle Pose and Shape from Lidar Data

Researchers have introduced a novel network architecture for jointly estimating the shape and pose of vehicles even from partial LiDAR observations. | Continue reading


@syncedreview.com | 4 years ago

Novel Attention Condensers Enable Deep Recognition Networks on Edge Devices

Novel attention condensers designed to enable the building of low-footprint, highly-efficient deep neural networks for on-device speech recognition on the edge. | Continue reading


@syncedreview.com | 4 years ago

Even the Best Language Models Don’t Have a Clue What They’re Doing

Researchers introduce a test covering topics such as elementary mathematics, designed to measure language models’ multitask accuracy. | Continue reading


@syncedreview.com | 4 years ago

Is OpenAI’s GPT-3 API Beta Pricing Too Rich for Researchers?

Although OpenAI hasn’t yet officially announced the GRT-3 pricing scheme, Branwen’s sneak peek has piqued the interest of the NLP community. | Continue reading


@syncedreview.com | 4 years ago

DeepMind Uses GNNs to Boost Google Maps ETA Accuracy by Up to 50%

DeepMind unveiled a partnership with Google Maps that has leveraged advanced GNNs to improve ETA accuracy. | Continue reading


@syncedreview.com | 4 years ago

IIIT Hyperbad’s ‘Wave2Lip’ Boosts Lip-Sync Video Performance

“Wav2Lip,” a novel lip-synchronization model that outperforms current approaches by a large margin in both quantitative metrics and human evaluations. | Continue reading


@syncedreview.com | 4 years ago

Nvidia Launches GeForce RTX 30 Series GPUs: ‘A Giant Step into the Future’

Nvidia CEO Jensen Huang today unveiled the company’s new GeForce RTX 30 Series GPUs. | Continue reading


@syncedreview.com | 4 years ago

Microsoft Researcher Single-Handedly Surveys TheSOTA in SignLanguage Recognition

Researcher composes a quantitative survey of the SOTA in sign language recognition (SLR). | Continue reading


@syncedreview.com | 4 years ago

Facebook One-Shot, On-Device Model Transforms Smartphone Pics into 3D Images

Facebook has introduced a model that turns common two-dimensional pictures into 3D photos. | Continue reading


@syncedreview.com | 4 years ago

Salesforce’s AI-Powered Economist to Optimize Income Equality and Productivity

The AI Economist uses a two-level RL framework where a collection of AI agents simulate how humans might react to various taxes in a principled economic simulation.  | Continue reading


@syncedreview.com | 4 years ago

Can AI Reimagine City Configuration and Automate Urban Planning?

Researchers propose reducing the workloads of urban planners by introducing deep learning systems to handle some of their responsibilities. | Continue reading


@syncedreview.com | 4 years ago

MIT CSAIL Model Identifies Manipulations Using Local Artifacts

Researchers proposed a new model that is designed to spot deepfakes by looking at subtle visual artifacts. | Continue reading


@syncedreview.com | 4 years ago

USC Proposes Monocular Real-Time Volumetric Performance Capture

A novel volumetric capture system that is capable of fully capturing clothed human bodies in real-time using only a single RGB webcam. | Continue reading


@syncedreview.com | 4 years ago

Using Deep RL to Model Human Locomotion Control in Neuromechanical Simulations

Researchers from Stanford University, UC Berkeley and CMU review neuromechanical simulations and DRL, with a focus on modelling the control of human locomotion. | Continue reading


@syncedreview.com | 4 years ago

Tesla Video Data Processing Supercomputer ‘Dojo’

Elon Musk tweeted that Tesla is recruiting AI or chip talents for the company’s neural network training supercomputer project “Dojo.” | Continue reading


@syncedreview.com | 4 years ago

Advancing Safety and Privacy for Trustworthy AI Inference Systems

Researchers from academia and industry offer input on the design, deployment, and operation of trustworthy AI inference systems. | Continue reading


@syncedreview.com | 4 years ago

How Smart Is Bert? Evaluating the Language Model’s Commonsense Knowledge

Researchers dive deep into the large language model to discover how it encodes the structured commonsense knowledge it leverages on downstream commonsense tasks. | Continue reading


@syncedreview.com | 4 years ago

Holicity: A City-Scale Dataset for Learning Holistic 3D Structures

HoliCity, a city-scale dataset and all-in-one data platform for research into learning abstracted high-level holistic 3D structures derived from city CAD (computer-aided design) models. | Continue reading


@syncedreview.com | 4 years ago

Google Delivers Accurate 3D Scene Reconstruction of Complex Outdoor Environment

Google researchers have introduced a series of extensions to the SOTA view-synthesis method Neural Radiance Fields (NeRF) that enable it to produce high-quality 3D representations of complex scenes… | Continue reading


@syncedreview.com | 4 years ago

Google AI ‘MediaPipe Iris’ Improves Iris Tracking and Distance Estimation

MediaPipe Iris, a novel machine learning model designed to deliver accurate iris estimation without using depth sensors. | Continue reading


@syncedreview.com | 4 years ago

Novel Encoder Architecture Boosts Facial Image-to-Image Translation

Researchers from Penta-AI and Tel-Aviv University introduce a generic image-to-image translation framework dubbed Pixel2Style2Pixel (pSp). | Continue reading


@syncedreview.com | 4 years ago

Trump Escalates His China Tech Ban from TikTok to WeChat

US President Donald Trump released two executive orders to ban the Chinese messaging app WeChat. | Continue reading


@syncedreview.com | 4 years ago

AI Generator Learns to ‘Draw’ Like Cartoonist Lee Mal-Nyeon in Just 10 Hours

A Seoul National University Master’s student and developer has trained a face generating model to transfer normal face photographs into cartoon images in the distinctive style of Lee Mal-nyeo… | Continue reading


@syncedreview.com | 4 years ago

Google ‘BigBird’ Achieves SOTA Performance on Long-Context NLP Tasks

BigBird is shown to dramatically improve performance across long-context NLP tasks, producing SOTA results in question answering and summarization. | Continue reading


@syncedreview.com | 4 years ago

Applying Linearly Scalable Transformers to Model Longer Protein Sequences

Researchers proposed a new transformer architecture called “Performer” — based on what they call fast attention via orthogonal random features (FAVOR). | Continue reading


@syncedreview.com | 4 years ago

Bridging the Gap Between Fully-Connected and Convolutional Nets

Unlike previous work that suggested fully-connected networks can only deliver subpar performance, Neyshabur’s experiments showed a significant performance jump. | Continue reading


@syncedreview.com | 4 years ago

New White-Box Framework Will Cartoonize Your World

This framework can generate high-quality cartoonized images with much-improved controllability. | Continue reading


@syncedreview.com | 4 years ago