Columbia University Model Learns Predictability From Unlabelled Video
Researchers propose a novel framework and hierarchical predictive model that learns to identify what is predictable from unlabelled video.
Tag: Research
Microsoft DeBERTa Tops Human Performance on SuperGLUE NLU Benchmark
A new model surpassed human baseline performance on the challenging natural language understanding benchmark.
For Its Latest Trick, OpenAI’s GPT-3 Generates Images From Text Captions
OpenAI has trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.
‘Neural Body’ Reconstructs Dynamic Human Bodies From Sparse Camera Views
The novel approach tackles dynamic 3D human-body synthesis from a sparse set of camera views, bettering existing methods on key metrics by significant margins.
PGDrive Simulator Generates Unlimited Diverse Driving Environments
Researchers proposed PGDrive, a driving simulator designed to evaluate and improve end-to-end driving agents’ generalization abilities.
Japanese Manga Translation Via Multimodal Context-Aware Framework
A new machine translation method enables global manga fans to enjoy immediate translations of their favourite Japanese comics.
Are RL Agents More Humanlike When Not Seeking Rewards? New Research from Vector Institute, University of Toronto & Google Brain
Researchers from Vector Institute, University of Toronto and Google Brain recently studied three common types of intrinsic motivation across seven agents, three Atari games, and the 3D game Minecraft.
Tsinghua University Releases First AutoML Toolkit for Graph Datasets & Tasks
Researchers from Tsinghua University have developed an AutoML framework and toolkit specifically designed for graph datasets and tasks.
Heidelberg University Researchers Combine CNNs and Transformers to Synthesize High-Resolution Images
Researchers combine the effectiveness of the inductive bias in CNNs with the expressivity of transformers to model and synthesize high resolution images.
URI Researchers Trained CNN Networks to ID mosquitos
Rapid and accurate identification of mosquitoes that transmit human pathogens such as malaria is an essential part of mosquito-borne disease surveillance.
2020 in Review: 10 AI Papers That Made an Impact
As part of our year-end series, Synced highlights 10 artificial intelligence papers that garnered extraordinary attention and accolades in 2020.
WILDS: Benchmarking Distribution Shifts in 7 Societally-Important Datasets
WILDS is an ambitious benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications.
NeurIPS 2020 | Teaching Transformers New Tricks
This year, 22 Transformer-related research papers were accepted by NeurIPS, the world’s most prestigious machine learning conference. Synced has selected ten of these works to showcase the latest Transformer trends.
Mila Proposes New Inductive Biases to Boost Deep Learning
Yoshua Bengio and Anirudh Goyal from Mila - Quebec AI Institute delve into human and non-human animal intelligence and how it can inform deep learning.
SlimGANs: Real-Time Adjustable Model Sizes
SlimGANs can easily change model sizes during runtime to implement quality-efficiency trade-offs based on practical needs.
MIT CSAIL Uses Deep Generative Model StyleGAN2 to Deliver SOTA Image Reconstruction Results
CSAIL researchers propose a framework for image reconstruction tasks using the state-of-the-art generative model StyleGAN2.
This Pizza Does Not Exist: StyleGAN2-Based Model Generates Photo-Realistic Pizza Images
The new AI-powered Multi-Ingredient Pizza Generator (MPG) can deliver all these mouth-watering pies and many more.
Can Autonomous Vehicles Self-Learn the Rules of the Road?
What if, instead of hard-coding road rules into self-driving algorithms, AI agents were free to come up with their own ways of safely and efficiently sharing the road?
NVIDIA Neural Talking-Head Synthesis Makes Video Conferencing 10x More Bandwidth Efficient
The approach dramatically reduces bandwidth requirements by sending only a keypoint representation [of faces] and reconstructing the source video on the receiver side with the help of generative adversarial networks (GANs) to synthesize the talking heads.
Airbus AI Introduces Natural Language QA System for Flight Crews
Airbus has developed a new Smart Librarian (SL) FCOM QA system comprising a dialogue engine, retriever (search engine), and QA module.
‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge
Google’s UK-based lab and research company DeepMind says its AlphaFold AI system has solved the protein folding problem, a grand challenge that has vexed the biology research community for half a century.
Facebook Proposes Free-Viewpoint Rendering on Monocular Video
Facebook’s new model enables free-viewpoint rendering of dynamic scenes in a single video.
USC & Amazon ‘SLADE’ Self-Training Framework Uses Unlabelled Data to Improve Information Retrieval
The SeLf-trAining framework for Distance mEtric learning (SLADE) framework combines self-supervised learning and distance metric learning methods to improve information retrieval performance.
University of Alberta U^2-Net: Generating Realistic Pencil Portraits Using Salient Object Detection
University of Alberta recently proposed U^2-Net, a novel deep network architecture that achieves very competitive performance in salient object detection.
McGill University, Facebook & Mila Release 14M Article NLP Pretraining Dataset for Medical Abbreviation Disambiguation
In EMNLP 2020, a Montreal-based research team introduced a large medical text dataset designed to boost abbreviation disambiguation in the medical domain.
UP-DETR: Unsupervised ‘Random Query Patch Detection’ Pretrains Transformers for Object Detection
A new study by South China University of Technology and Tencent WeChat AI researchers is the latest fruitful attempt to utilize transformer architectures in object detection.
DeepMind Open-Sources Lab2D: Environmental Design for Multi-Agent RL Research
A new DeepMind scalable environment simulator takes a digital approach to the question, enabling the examination of environmental factors on AI agents.
MIT CSAIL & Amazon AI Framework Maps Raw Audio Directly to Semantics
New Spoken Language Understanding (SLU) research from MIT CSAIL and Amazon AI introduces step-skipping semi-supervised frameworks that take speech as input and achieve performance competitive to systems leveraging oracle text.
IBM Fine-Grained Visual Recognition Powers AR Tech Support
“Our research provides enriched AR user experiences by enabling a more fine-grained visual recognition feature in AR, which is desirable in a wide range of application scenarios including technical support,” IBM researchers say.
Google & DeepMind Debut Benchmark for Long-Range Transformers
Google Research and DeepMind debut Long-Range Arena (LRA) benchmark for Transformer research on tasks with long sequence lengths.
Google Brain Paper Demystifies Learned Optimizers
Google Brain ICLR 2021 submission analyzes learned optimizers’ performance advantage over well-tuned baseline optimizers.
Nvidia Introduces Modular Primitives for High-Performance Differentiable Rendering
Researchers introduced a modular primitive that uses existing, highly optimized hardware graphics pipelines to deliver performance superior to previous differentiable rendering systems.
Amazon Alexa AI’s ‘Language Model Is All You Need’ Explores NLU as QA
Amazon Alexa AI paper asks whether NLU problems could be mapped to question-answering (QA) problems using transfer learning.
Facebook AI Says Class Selectivity In Neurons May Impair DNN Performance
Facebook AI says DNNs can perform well without class specific neurons and overreliance on intuition-based methods for understanding DNNs can be misleading.
DeepMind Introduces Algorithms for Causal Reasoning in Probability Trees
Probability trees may have been around for decades, but they have received little attention from the AI and ML community.
Amazon’s BERT Optimal Subset: 7.9x Faster & 6.3x Smaller Than BERT
Amazon extracts an optimal subset of architectural parameters for BERT architecture by applying recent breakthroughs in algorithms for neural architecture search.
Google ‘mT5’ Pretrained Text-to-Text Transformer Achieves SOTA Performance on Multilingual Benchmarks
Google recently introduced mT5, a multilingual variant of its “Text-to-Text Transfer Transformer” (T5), pretrained on a new Common Crawl-based dataset covering 101 languages.
ICLR 2021 Submission | ‘Lambda Networks’ Achieve SOTA Accuracy, Save Massive Memory
ICLR 2021 submission proposes LambdaNetworks, a transformer-specific method that reduces costs of modeling long-range interactions for CV and other applications.
Facebook AI Model Directly Translates 100 Languages Without Using English Data
Facebook AI open-sourced a multilingual machine translation (MMT) model that translates between any pair of 100 languages without relying on English data.
UK Researchers Say AI Needs More Animal Sense
The UK researchers identify just how much AI research might benefit from the field of animal cognition.