39 citations · 136 across the 17 of their papers we have counts for
20 papers
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data
Ziyi Yang, Mahmoud Khademi, Yichong Xu +16
The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encod…
i-Code: An Integrative and Composable Multimodal Learning Framework
Ziyi Yang, Yuwei Fang, Chenguang Zhu +17
Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview. Most current pretraining methods, however, are limited to…
Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas +5
The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity. In this work, we investigate how multi-lingual Automatic Speech R…
Sequence-level self-learning with multiple hypotheses
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur +4
In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech…
Dynamic Gradient Aggregation for Federated Domain Adaptation
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr +2
In this paper, a new learning algorithm for Federated Learning (FL) is introduced. The proposed scheme is based on a weighted gradient aggregation using two-step optimization to of…
Federated Transfer Learning with Dynamic Gradient Aggregation
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr +2
In this paper, a Federated Learning (FL) simulation platform is introduced. The target scenario is Acoustic Model training based on this platform. To our knowledge, this is the fir…
Sleeping is Efficient: MIS in -rounds Node-averaged Awake Complexity
Soumyottam Chatterjee, Robert Gmyr, Gopal Pandurangan
Maximal Independent Set (MIS) is one of the fundamental problems in distributed computing. The round (time) complexity of distributed MIS has traditionally focused on the \emph{wor…
TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising
Ziyi Yang, Chenguang Zhu, Robert Gmyr +3
Text summarization aims to extract essential information from a piece of text and transform the text into a concise version. Existing unsupervised abstractive summarization models…
Leveraging Lead Bias for Zero-shot Abstractive News Summarization
Chenguang Zhu, Ziyi Yang, Robert Gmyr +2
A typical journalistic convention in news articles is to deliver the most salient information in the beginning, also known as the lead bias. While this phenomenon can be exploited…
CADbots: Algorithmic Aspects of Manipulating Programmable Matter with Finite Automata
Sándor P. Fekete, Robert Gmyr, Sabrina Hugo +3
We contribute results for a set of fundamental problems in the context of programmable matter by presenting algorithmic methods for evaluating and manipulating a collective of part…
Time-Message Trade-Offs in Distributed Algorithms
Robert Gmyr, Gopal Pandurangan
This paper focuses on showing time-message trade-offs in distributed algorithms for fundamental problems such as leader election, broadcast, spanning tree (ST), minimum spanning tr…
Distributed Computation in Node-Capacitated Networks
John Augustine, Mohsen Ghaffari, Robert Gmyr +4
In this paper, we study distributed graph algorithms in networks in which the nodes have a limited communication capacity. Many distributed systems are built on top of an underlyin…
Convex Hull Formation for Programmable Matter
Joshua J. Daymude, Robert Gmyr, Kristian Hinnenthal +3
We envision programmable matter as a system of nano-scale agents (called particles) with very limited computational capabilities that move and compute collectively to achieve a des…
Improved Leader Election for Self-Organizing Programmable Matter
Joshua J. Daymude, Robert Gmyr, Andrea W. Richa +2
We consider programmable matter that consists of computationally limited devices (called particles) that are able to self-organize in order to achieve some collective goal without…
On the Runtime of Universal Coating for Programmable Matter
Joshua J. Daymude, Zahra Derakhshandeh, Robert Gmyr +4
Imagine coating buildings and bridges with smart particles (also coined smart paint) that monitor structural integrity and sense and report on traffic and wind loads, leading to te…
Universal Coating for Programmable Matter
Zahra Derakhshandeh, Robert Gmyr, Andrea W. Richa +2
The idea behind universal coating is to have a thin layer of a specific substance covering an object of any shape so that one can measure a certain condition (like temperature or c…
An Algorithmic Framework for Shape Formation Problems in Self-Organizing Particle Systems
Zahra Derakhshandeh, Robert Gmyr, Andrea W. Richa +2
Many proposals have already been made for realizing programmable matter, ranging from shape-changing molecules, DNA tiles, and synthetic cells to reconfigurable modular robotics. E…
Leader Election and Shape Formation with Self-Organizing Programmable Matter
Joshua J. Daymude, Zahra Derakhshandeh, Robert Gmyr +4
We consider programmable matter consisting of simple computational elements, called particles, that can establish and release bonds and can actively move in a self-organized way, a…
Infinite Object Coating in the Amoebot Model
Zahra Derakhshandeh, Robert Gmyr, Andrea W. Richa +3
The term programmable matter refers to matter which has the ability to change its physical properties (shape, density, moduli, conductivity, optical properties, etc.) in a programm…
Ameba-inspired Self-organizing Particle Systems
Shlomi Dolev, Robert Gmyr, Andrea W. Richa +1
Particle systems are physical systems of simple computational particles that can bond to neighboring particles and use these bonds to move from one spot to another (non-occupied) s…