A low-cost robot ready for any obstacle

Researchers have designed a robotic system that enables a low-cost and relatively small legged robot to climb and descend stairs nearly its height; traverse rocky, slippery, uneven, steep and varied terrain; walk across gaps; scale rocks and curbs; and even operate in the dark.

Research ushers in a ‘new frontier’ in tackling global poverty

With electricity comes prosperity, right? The answer might seem obvious—that electricity is key to economic growth and other societal benefits like better health. But in the world’s most impoverished regions, where resources to improve livelihoods are scarce, it’s not clear how much better off people are when they have access to electrical power.

Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer

This paper was accepted at the workshop “Self-Supervised Learning – Theory and Practice” at NeurIPS 2022. Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with respect to the target label distribution. This in turn moves the learned …

Mean Estimation with User-level Privacy under Data Heterogeneity

A key challenge in many modern data analysis tasks is that user data is heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distribution. This is true, for example in language data, where different speech styles result in data …

Continuous Soft Pseudo-Labeling in ASR

This paper was accepted at the workshop “I Can’t Believe It’s Not Better: Understanding Deep Learning Through Empirical Falsification” Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and generating pseudo-labels (PLs) with …

Helping VFX studios pave a path to the cloud

By: Peter Cioni (Netflix), Alex Schworer (Netflix), Mac Moore (Conductor Tech.), Rachel Kelley (AWS), Ranjit Raju (AWS) Rendering is core to the VFX process VFX studios around the world create amazing imagery for Netflix productions. Nearly every show that is produced today includes digital visual effects, from the creatures in Stranger Things, to recreating historic London in …