activity
20192021
most citedEvading Malware Classifiers via Monte Carlo Mutant Feature Discovery

3 citations · 6 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CL2021

Neural Variational Learning for Grounded Language Acquisition

Nisha Pillai, Cynthia Matuszek, Francis Ferraro

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a…

cs.CR20213 cited

Evading Malware Classifiers via Monte Carlo Mutant Feature Discovery

John Boutsikas, Maksim E. Eren, Charles Varga +3

The use of Machine Learning has become a significant part of malware detection efforts due to the influx of new malware, an ever changing threat landscape, and the ability of Machi…

cs.RO2020

Sampling Approach Matters: Active Learning for Robotic Language Acquisition

Nisha Pillai, Edward Raff, Francis Ferraro +1

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora. We present an exploration of active learning ap…

cs.CV20202 cited

Practical Cross-modal Manifold Alignment for Grounded Language

Andre T. Nguyen, Luke E. Richards, Gaoussou Youssouf Kebe +4

We propose a cross-modality manifold alignment procedure that leverages triplet loss to jointly learn consistent, multi-modal embeddings of language-based concepts of real-world it…

cs.RO20201 cited

Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning

Patrick Jenkins, Rishabh Sachdeva, Gaoussou Youssouf Kebe +7

Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the da…

cs.LG2019

Planning with Abstract Learned Models While Learning Transferable Subtasks

John Winder, Stephanie Milani, Matthew Landen +5

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple…