Search Results for author:
Found 30 papers, 3 papers with code
Topological Signatures of Adversaries in Multimodal Alignments
Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks.
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
We introduce a novel method to enhance cross-language code translation from Fortran to C++ by integrating task-specific embedding alignment into a Retrieval-Augmented Generation (RAG) framework.
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning
HEAL computes level/depth-wise contrastive losses and incorporates hierarchical penalties to align embeddings with the underlying relationships in label hierarchies.
Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty
In this study, we propose PatchFinder, an algorithm that builds upon VLMs to improve information extraction.
Benchmarking Large Language Models with Integer Sequence Generation Tasks
This paper presents a novel benchmark where the large language model (LLM) must write code that computes integer sequences from the Online Encyclopedia of Integer Sequences (OEIS), a widely-used resource for mathematical sequences.
Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization
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.
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial examples.
LaFA: Latent Feature Attacks on Non-negative Matrix Factorization
However, the introduction of powerful computational tools such as Pytorch enables the computation of gradients of the latent features with respect to the original data, raising concerns about NMF's reliability.
Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs
Additionally, Low-Rank Economic Tensor-Train Adaptation (LoRETTA), which utilizes tensor train decomposition, has not yet achieved the level of compression necessary for fine-tuning very large scale models with limited resources.
Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation
The advent of large language models (LLMs) has significantly advanced the field of code translation, enabling automated translation between programming languages.
TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs
Topic modeling is a technique for organizing and extracting themes from large collections of unstructured text.
Binary Bleed: Fast Distributed and Parallel Method for Automatic Model Selection
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.
Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
In this paper, we introduce innovative approaches for accelerating the Jacobi method for matrix diagonalization, specifically through the formulation of large matrix diagonalization as a Semi-Markov Decision Process and small matrix diagonalization as a Markov Decision Process.
Accelerating Matrix Diagonalization through Decision Transformers with Epsilon-Greedy Optimization
This paper introduces a novel framework for matrix diagonalization, recasting it as a sequential decision-making problem and applying the power of Decision Transformers (DTs).
Cyber-Security Knowledge Graph Generation by Hierarchical Nonnegative Matrix Factorization
One of the challenges in constructing a KG from scientific literature is the extraction of ontology from unstructured text.
Interactive Distillation of Large Single-Topic Corpora of Scientific Papers
Given a small initial "core" corpus of papers, we build a citation network of documents.
MalwareDNA: Simultaneous Classification of Malware, Malware Families, and Novel Malware
Here we introduce and showcase preliminary capabilities of a new method that can perform precise identification of novel malware families, while also unifying the capability for malware/benign-ware classification and malware family classification into a single framework.
Robust Adversarial Defense by Tensor Factorization
This study underscores the potential of integrating tensorization and low-rank decomposition as a robust defense against adversarial attacks in machine learning.
Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution
Matrix diagonalization is at the cornerstone of numerous fields of scientific computing.
SeNMFk-SPLIT: Large Corpora Topic Modeling by Semantic Non-negative Matrix Factorization with Automatic Model Selection
As the amount of text data continues to grow, topic modeling is serving an important role in understanding the content hidden by the overwhelming quantity of documents.
FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation
Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations.
Distributed Out-of-Memory NMF on CPU/GPU Architectures
In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems.
Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments
We present a new four-pronged approach to build firefighter's situational awareness for the first time in the literature.
A deep Q-Learning based Path Planning and Navigation System for Firefighting Environments
Live fire creates a dynamic, rapidly changing environment that presents a worthy challenge for deep learning and artificial intelligence methodologies to assist firefighters with scene comprehension in maintaining their situational awareness, tracking and relay of important features necessary for key decisions as they tackle these catastrophic events.
An embedded deep learning system for augmented reality in firefighting applications
Firefighting is a dynamic activity, in which numerous operations occur simultaneously.
A Novel Indoor Positioning System for unprepared firefighting scenarios
Situational awareness and Indoor location tracking for firefighters is one of the tasks with paramount importance in search and rescue operations.
Distributed Non-Negative Tensor Train Decomposition
Tensor train (TT) is a state-of-the-art tensor network introduced for factorization of high-dimensional tensors.
Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning
We then use our small set of manually labeled patent diagram images via transfer learning to adapt the image search from sketches of natural images to diagrams.
Learning Spatial Relationships between Samples of Patent Image Shapes
Binary image based classification and retrieval of documents of an intellectual nature is a very challenging problem.
A Deep Learning Framework for Detection of Targets in Thermal Images to Improve Firefighting
Intelligent detection and processing capabilities can be instrumental to improving the safety, efficiency, and successful completion of rescue missions conducted by firefighters in emergency first response settings.
