Explore the latest research from Facebook

All Publications

October 1, 2021 Hung Le, Chinnadhurai Sankar, Seungwhan Moon, Ahmad Beirami, Alborz Geramifard, Satwik Kottur
Paper

DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

The dataset is designed to contain minimal biases and has detailed annotations for the different types of reasoning over the spatio-temporal space of video. Dialogues are synthesized over multiple question turns, each of which is injected with a set of cross-turn semantic relationships. We use DVD to analyze existing approaches, providing interesting insights into their abilities and limitations.
Paper
August 31, 2021 Chunyang Wu, Zhiping Xiu, Yangyang Shi, Ozlem Kalinli, Christian Fuegen, Thilo Koehler, Qing He
Paper

Transformer-based Acoustic Modeling for Streaming Speech Synthesis

To address the complexity issue in speech synthesis domain, this paper proposes an efficient transformer-based acoustic model that is constant-speed regardless of input sequence length, making it ideal for streaming speech synthesis applications.
Paper
August 29, 2021 Anurag Kumar, Yun Wang, Vamsi Krishna Ithapu, Christian Fuegen
Paper

Do Sound Event Representations Generalize To Other Audio Tasks? A Case Study In Audio Transfer Learning

In this paper, we investigate the transfer learning capacity of audio representations obtained from neural networks trained on a large-scale sound event detection dataset.
Paper
August 20, 2021 Virginie Do, Jamal Atif, Jérôme Lang, Nicolas Usunier
Paper

Online Selection of Diverse Committees

We study three methods, theoretically and experimentally: a greedy algorithm that includes volunteers as long as proportionality is not violated; a non-adaptive method that includes a volunteer with a probability depending only on their features, assuming that the joint feature distribution in the volunteer pool is known; and a reinforcement learning based approach when this distribution is not known a priori but learnt online.
Paper
August 9, 2021 Jungdam Won, Deepak Gopinath, Jessica Hodgins
Paper

Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports

In this paper, we develop a learning framework that generates control policies for physically simulated athletes who have many degrees-of-freedom. Our framework uses a two step-approach, learning basic skills and learning boutlevel strategies, with deep reinforcement learning, which is inspired by the way that people how to learn competitive sports.
Paper
August 1, 2021 Pedro Rodriguez, Joe Barrow, Alexander Hoyle, John P. Lalor, Robin Jia, Jordan Boyd-Graber
Paper

Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?

Rather than replace leaderboards, we advocate a re-imagining so that they better highlight if and where progress is made. Building on educational testing, we create a Bayesian leaderboard model where latent subject skill and latent item difficulty predict correct responses.
Paper
July 24, 2021 Jonathan Lorraine, Jack Parker-Holder, Paul Vicol, Aldo Pacchiano, Luke Metz, Tal Kachman, Jakob Foerster
Paper

Using Bifurcations for Diversity in Differentiable Games

RR is designed for conservative gradient systems (i.e. settings involving a single loss function), where it branches at saddles – the only relevant bifurcation points. We generalize this idea to non-conservative, multi-agent gradient systems by identifying new types of bifurcation points and proposing a method to follow eigenvectors with complex eigenvalues.
Paper
July 23, 2021 David Eriksson, Martin Jankowiak
Paper

High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspaces

In an extensive suite of experiments comparing to existing methods for high-dimensional BO we demonstrate that our algorithm, Sparse Axis-Aligned Subspace BO (SAASBO), achieves excellent performance on several synthetic and real-world problems without the need to set problem-specific hyperparameters.
Paper
July 18, 2021 Stephane d’Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun
Paper

ConViT- Improving Vision Transformers with Soft Convolutional Inductive Biases

In this paper, we ask the following question: is it possible to combine the strengths of these two architectures while avoiding their respective limitations? To this end, we introduce gated positional self-attention (GPSA), a form of positional self-attention which can be equipped with a “soft” convolutional inductive bias.
Paper
July 18, 2021 Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra
Paper

AlphaNet: Improved Training of Supernets with Alpha-Divergence

In this work, we propose to improve the supernet training with a more generalized α-divergence. By adaptively selecting the α-divergence, we simultaneously prevent the over-estimation or under-estimation of the uncertainty of the teacher model.
Paper