AI Technology & Industry Review
A Yann LeCun team proposes dictionary learning to provide detailed visualizations of transformer representations and insights into semantic structures such as word-level disambiguation, sentence-level pattern formation, and long-range dependency captured by transformers.
Researchers from UC Berkeley and Google Research have introduced BoTNet, a “conceptually simple yet powerful” backbone architecture that boosts performance on computer vision (CV) tasks such as image classification, object detection and instance segmentation.
Researchers from the University of Wisconsin-Madison, UC Berkeley, Google Brain and American Family Insurance propose Nyströmformer, an adaption of the Nystrom method that approximates standard self-attention with O(n) complexity.
Augmented Temporal Contrast (ATC), a new unsupervised learning (UL) task for learning visual representations agnostic to rewards and without degrading the control policy.
Researchers introduce a test covering topics such as elementary mathematics, designed to measure language models’ multitask accuracy.
Researchers from Stanford University, UC Berkeley and CMU review neuromechanical simulations and DRL, with a focus on modelling the control of human locomotion.
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.
“Unselfie,” a novel photographic transformation model that can automatically translate selfies into neutral-pose portraits.
A team of researchers from Facebook and UC Berkeley has proposed a new paradigm for computer vision.
UC Berkeley and Adobe Research have introduced a “universal” detector that can distinguish real images from generated images regardless of what architectures and/or datasets were used for training.
A recent paper accepted by ICLR 2020 proposes a new transformer model called “Reformer” which achieves impressive performance even when running on only a single GPU.
Berkeley Artificial Intelligence Research (BAIR) has introduced a new reinforcement learning (RL) method, Stochastic Optimal Control with Latent Representations (SOLAR), which can help robots quickly learn tasks such as stacking blocks or pushing objects from visual inputs.
Synced Global AI Weekly January 6th
UC Berkeley researchers have published a paper demonstrating how Deep Reinforcement Learning can be used to control dexterous robot hands for complicated tasks. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations proposes a low-cost and high-efficiency control method that uses demonstration and simulation techniques to accelerate the learning process.
Compositing multiple objects from different sources into one image is a formidable computer graphics challenge involving relative scaling, spatial layout, occlusion, and viewpoint transformation of objects from the 3D world to a 2D image.
Electrifying an entire dance club is easy if you have killer moves like John Travolta in Saturday Night Fever. But for the rest of us, not so much. We may shake our butts and swing our arms, but let’s face it: some people just can’t dance. But now there’s hope, thanks to AI.
UC Berkeley’s Artificial Intelligence Research Lab (BAIR) has open-sourced their newest driving database, BDD100K, which contains over 100k videos of driving experience, each running 40 seconds at 30 frames per second.
To boost learning research aimed at endowing robots with better generalization capabilities, Yi Wu from UC Berkeley and Yuxin Wu, Georgia Gkioxari, and Yuandong Tian from Facebook AI research recently published the paper Building Generalizable Agents with a Realistic and Rich 3D Environment.