We introduce CompilerGym, a set of environments for real world compiler optimization tasks, and a toolkit for exposing new optimization tasks to compiler researchers. CompilerGym...
Our study shows that denoising autoencoders, such as BEiT or a variant that we introduce in this paper, are more robust to the type and size of the pre-training data than popular self-supervised methods trained by comparing image embeddings.
In this paper, by decoupling the concepts of modeling units and label topologies and building proper numerator/denominator graphs accordingly, we establish a generalized framework for hybrid acoustic modeling (AM).
We describe how the priorities evolved over time as a result of hardware trends and extensive experiences running RocksDB at scale in production at a number of organizations: from optimizing write amplification, to space amplification, to CPU utilization.
In this paper, we propose a new parametrization to supervised learning on state-action data to stably predict at longer horizons – that we call a trajectory-based model.
We then train a new two-layer codec avatar with separate modeling of the upper clothing and the inner body layer. To learn the interaction between the body dynamics and clothing states, we use a temporal convolution network to predict the clothing latent code based on a sequence of input skeletal poses. We show photorealistic animation output for three different actors, and demonstrate the advantage of our clothed-body avatars over the single-layer avatars used in previous work.
In this paper, we formulate the problem of dense subgraph detection on multi-layered networks based on cross-layer consistency principle.
In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the exponential moving average (EMA) of the student model parameters.
We show that this discrepancy can persist even when padding is applied. In particular, with the commonly-used zero-padding, foveation effects are significantly reduced but not...
We propose a model for grounding language in 3D scenes that bypasses box proposal bottlenecks with three main innovations: i) Iterative attention across the language stream, the...
