11 citations · 26 across the 8 of their papers we have counts for
8 papers
The Landscape and Challenges of HPC Research and LLMs
Le Chen, Nesreen K. Ahmed, Akash Dutta +14
Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning. Both encoder-decoder models and prompt-based techniques ha…
MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks
Tal Kadosh, Niranjan Hasabnis, Vy A. Vo +10
With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programmin…
Scope is all you need: Transforming LLMs for HPC Code
Tal Kadosh, Niranjan Hasabnis, Vy A. Vo +9
With easier access to powerful compute resources, there is a growing trend in the field of AI for software development to develop larger and larger language models (LLMs) to addres…
Memory in humans and deep language models: Linking hypotheses for model augmentation
Omri Raccah, Phoebe Chen, Ted L. Willke +2
The computational complexity of the self-attention mechanism in Transformer models significantly limits their ability to generalize over long temporal durations. Memory-augmentatio…
Memory-Augmented Graph Neural Networks: A Brain-Inspired Review
Guixiang Ma, Vy A. Vo, Theodore Willke +1
We provide a comprehensive review of the existing literature on memory-augmented GNNs. We review these works through the lens of psychology and neuroscience, which has several esta…
End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning
Yao Xiao, Guixiang Ma, Nesreen K. Ahmed +4
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (P…
Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay
Hsiang-Yun Sherry Chien, Javier S. Turek, Nicole Beckage +3
Sequential information contains short- to long-range dependencies; however, learning long-timescale information has been a challenge for recurrent neural networks. Despite improvem…
Procrustean Orthogonal Sparse Hashing
Mariano Tepper, Dipanjan Sengupta, Ted Willke
Hashing is one of the most popular methods for similarity search because of its speed and efficiency. Dense binary hashing is prevalent in the literature. Recently, insect olfactio…