AI Technology & Industry Review
TaBERT-powered neural semantic parsers showed performance improvements on the challenging benchmark WikiTableQuestions and demonstrated competitive performance on the text-to-SQL dataset Spider.
Researchers proposed a Taylor Expansion Policy Optimization (TayPO) framework that combines two leading algorithmic improvement methods.
The acceptance rate of 21.8 percent is slightly lower than 2019’s 22.6 percent (774 accepted papers from 3,424 submissions).
DeepMind introduced a new approach designed to improve the generalizability and efficiency of algorithms represented by neural networks.
To promote fairer ML systems, the team introduced a collaborative causal theory formation that incorporates diverse stakeholder perspectives for discovering and considering societal context.
DeepMind researchers call attention to another “fundamentally novel” development in AI research — deep reinforcement learning (deep RL) — which they believe also has vital implications for neuroscience and deserves more attention from neuroscientists.
The post highlights perceived peer-review problems, the reproducibility crisis, and ethics and diversity issues.
A team of researchers proposed a novel three-stage learning framework that includes scene context to generate long-term 3D human motion prediction when given a single scene image and 2D pose histories.
Researchers propose a neuro-symbolic hybrid approach to address the challenge of creativity in generative art.
Organizers of the 58th Annual Meeting of the Association for Computational Linguistics (ACL) today announced their Best Paper Awards.
Researchers introduce a novel Physical Scene Graphs (PSG) approach designed to obtain a better structured understanding of visual scenes.
The proposed method generalizes well across various degrees of eye openness, different identities, and combinations of eye and lower facial expressions.
Organizers of the 37th International Conference on Machine Learning (ICML) have announced this year’s Test of Time award, which goes to a team from the California Institute of Technology, University of Pennsylvania, Saarland University.
NLE is a procedurally generated environment for testing the robustness and systematic generalization of RL agents.
Turing Award Winner and Facebook Chief AI Scientist Yann LeCun has announced his exit from Twitter after getting involved in a long and often acrimonious dispute regarding racial biases in AI.
A team of researchers from Princeton, DeepMind and New York University have introduced a new method that extracts symbolic representations from deep learning models by introducing strong induction biases.
This paper presents a novel contrastive framework for unsupervised graph representation learning.
The researchers introduce sinusoidal representation networks (SIRENs) as a method for leveraging periodic activation functions for implicit neural representations.
DeepMind researchers released several new models and a tutorial for their dm_control software stack for physics-based simulation and reinforcement learning environments using MuJoCo physics.
Researchers have proposed the use of Fourier feature mapping with MLPs in order to learn high-frequency functions in low-dimensional problem domains.
Google Brain in Zürich and DeepMind London researchers believe one of the world’s most popular image databases may need a makeover.
Following on the February release of its contrastive learning framework SimCLR, the same team of Google Brain researchers guided by Turing Award honouree Dr. Geoffrey Hinton has presented SimCLRv2, an upgraded approach that boosts the SOTA results by 21.6 percent.
Researchers from the University of Washington, Salesforce Research and Allen Institute for Artificial Intelligence have introduced a graph-based method that retrieves reasoning paths to boost multi-hop open-domain question answering.
Large transformer-based language models trained on pixel sequences can generate coherent images without the use of labels.
A team of researchers from Google Brain have proposed a rethink of the dominant computer vision paradigm of pre-training.
Researchers have proposed a novel framework that learns fast and dynamic character interactions.
Covariant last month secured a US$40 million Series B funding round led by Index Ventures to push its total funding to US$67 million.
Researchers from Fudan University and Microsoft have proposed a novel seq2seq architecture that generates dance sequences for music clips running a minute or longer.
Facebook and Kaggle are facing an online backlash after the apparent winners of the Deepfake Detection Challenge (DFDC) were disqualified.
A team of researchers from Facebook and UC Berkeley has proposed a new paradigm for computer vision.
Researchers from the University of Tokyo and Google Research have proposed a new metric for RL performance and novel BREMEN algorithm designed to manage the costs and risks of new policy deployment.
In a recent Google AI team blog post, researchers report on recent efforts and progress in the field of language translation, especially with resource-poor languages.
Neuropod, an open-source library that provides a uniform interface for running deep learning (DL) models from multiple frameworks in C++ and Python.
DeepMind researchers have developed EATS, a generative model trained adversarially in an end-to-end manner that achieves performance comparable to SOTA models.
A team of researchers from the Chinese Academy of Sciences and the City University of Hong Kong has introduced a local-to-global approach that can generate lifelike human portraits from relatively rudimentary sketches.
Researchers from Katholieke Universiteit Leuven in Belgium and ETH Zürich in a recent paper propose a two-step approach for unsupervised classification.
DeepMind researchers introduce a framework that aims to solve the problem by enabling simple RL agent implementations to be run at different scales of execution.
Rather than simply treating AI as a tool to be leveraged, this approach reimagines AI as a collaborator that learns from a developer’s needs and subsequently proposes multiple design approaches with different trade-offs in order to enable a rapid and iterative approach to model building.
A total of 1,088 papers out of 4,990 submissions made it to the prestigious machine learning conference.
Researchers add syntactic biases to determine whether and where they can help BERT achieve better understanding.