1 code implementation • 5 Dec 2024 • Manish Bhattarai, Ryan Barron, Maksim Eren, Minh Vu, Vesselin Grantcharov, Ismael Boureima, Valentin Stanev, Cynthia Matuszek, Vladimir Valtchinov, Kim Rasmussen, Boian Alexandrov
HEAL computes level/depth-wise contrastive losses and incorporates hierarchical penalties to align embeddings with the underlying relationships in label hierarchies.
no code implementations • 27 Nov 2024 • Siddhant Gupta, Fred Lu, Andrew Barlow, Edward Raff, Francis Ferraro, Cynthia Matuszek, Charles Nicholas, James Holt
A strategy used by malicious actors is to "live off the land," where benign systems and tools already available on a victim's systems are used and repurposed for the malicious actor's intent.
no code implementations • 3 Oct 2024 • Ryan C. Barron, Ves Grantcharov, Selma Wanna, Maksim E. Eren, Manish Bhattarai, Nicholas Solovyev, George Tompkins, Charles Nicholas, Kim Ø. Rasmussen, Cynthia Matuszek, Boian S. Alexandrov
In this paper, we introduce SMART-SLIC, a highly domain-specific LLM framework, that integrates RAG with KG and a vector store (VS) that store factual domain specific information.
1 code implementation • 26 Jul 2024 • Ryan Barron, Maksim E. Eren, Manish Bhattarai, Ismael Boureima, Cynthia Matuszek, Boian S. Alexandrov
In our experiments, we demonstrate the reduced search space gain over a naive sequential search of the ideal k and the accuracy of the Binary Bleed in identifying the correct k for NMFk, K-Means pyDNMFk, and pyDRESCALk with Silhouette and Davies Boulding scores.
no code implementations • 1 Apr 2024 • Casey Kennington, Malihe Alikhani, Heather Pon-Barry, Katherine Atwell, Yonatan Bisk, Daniel Fried, Felix Gervits, Zhao Han, Mert Inan, Michael Johnston, Raj Korpan, Diane Litman, Matthew Marge, Cynthia Matuszek, Ross Mead, Shiwali Mohan, Raymond Mooney, Natalie Parde, Jivko Sinapov, Angela Stewart, Matthew Stone, Stefanie Tellex, Tom Williams
The ability to interact with machines using natural human language is becoming not just commonplace, but expected.
no code implementations • 24 Mar 2024 • Ryan Barron, Maksim E. Eren, Manish Bhattarai, Selma Wanna, Nicholas Solovyev, Kim Rasmussen, Boian S. Alexandrov, Charles Nicholas, Cynthia Matuszek
One of the challenges in constructing a KG from scientific literature is the extraction of ontology from unstructured text.
no code implementations • 25 Dec 2023 • Tirth Patel, Fred Lu, Edward Raff, Charles Nicholas, Cynthia Matuszek, James Holt
Industry practitioners care about small improvements in malware detection accuracy because their models are deployed to hundreds of millions of machines, meaning a 0. 1\% change can cause an overwhelming number of false positives.
1 code implementation • 2 Dec 2023 • Mohammad Mahmudul Alam, Edward Raff, Tim Oates, Cynthia Matuszek
In the case of DDx, the proposed network has achieved a mean accuracy of 99. 82% and a mean F1 score of 0. 9472.
no code implementations • 17 Feb 2023 • Luke E. Richards, Edward Raff, Cynthia Matuszek
Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks.
no code implementations • 27 Dec 2021 • Gaoussou Youssouf Kebe, Luke E. Richards, Edward Raff, Francis Ferraro, Cynthia Matuszek
Learning to understand grounded language, which connects natural language to percepts, is a critical research area.
no code implementations • 23 Sep 2021 • Luke E. Richards, André Nguyen, Ryan Capps, Steven Forsythe, Cynthia Matuszek, Edward Raff
In this work we note that as studied, current transfer attack research has an unrealistic advantage for the attacker: the attacker has the exact same training data as the victim.
no code implementations • 20 Jul 2021 • 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.
2 code implementations • 15 Jun 2021 • John Boutsikas, Maksim E. Eren, Charles Varga, Edward Raff, Cynthia Matuszek, Charles Nicholas
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 Machine Learning methods to discover meaningful distinctions between malicious and benign software.
no code implementations • 16 Nov 2020 • Nisha Pillai, Edward Raff, Francis Ferraro, Cynthia Matuszek
Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora.
no code implementations • 1 Sep 2020 • Andre T. Nguyen, Luke E. Richards, Gaoussou Youssouf Kebe, Edward Raff, Kasra Darvish, Frank Ferraro, Cynthia Matuszek
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 items.
no code implementations • 29 Jul 2020 • Patrick Jenkins, Rishabh Sachdeva, Gaoussou Youssouf Kebe, Padraig Higgins, Kasra Darvish, Edward Raff, Don Engel, John Winder, Francis Ferraro, Cynthia Matuszek
Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI.
no code implementations • 16 Dec 2019 • John Winder, Stephanie Milani, Matthew Landen, Erebus Oh, Shane Parr, Shawn Squire, Marie desJardins, Cynthia Matuszek
We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
no code implementations • WS 2019 • Caroline Kery, Francis Ferraro, Cynthia Matuszek
In this paper we describe a multilingual grounded language learning system adapted from an English-only system.
no code implementations • 27 Jun 2012 • Cynthia Matuszek, Nicholas FitzGerald, Luke Zettlemoyer, Liefeng Bo, Dieter Fox
As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them.