no code implementations • 9 Apr 2024 • Waqwoya Abebe, Jan Strube, Luanzheng Guo, Nathan R. Tallent, Oceane Bel, Steven Spurgeon, Christina Doty, Ali Jannesari
To enable rapid adaptation of the best segmentation technology, we propose the concept of semantic boosting: given a zero-shot foundation model, guide its segmentation and adjust results to match domain expectations.
no code implementations • 12 Mar 2024 • Chandan Kumar, Jansel Herrera-Gerena, John Just, Matthew Darr, Ali Jannesari
The rapid proliferation of digital content and the ever-growing need for precise object recognition and segmentation have driven the advancement of cutting-edge techniques in the field of object classification and segmentation.
no code implementations • 21 Feb 2024 • Chandan Kumar, Jansel Herrera-Gerena, John Just, Matthew Darr, Ali Jannesari
Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy environments.
no code implementations • 3 Feb 2024 • Le Chen, Nesreen K. Ahmed, Akash Dutta, Arijit Bhattacharjee, Sixing Yu, Quazi Ishtiaque Mahmud, Waqwoya Abebe, Hung Phan, Aishwarya Sarkar, Branden Butler, Niranjan Hasabnis, Gal Oren, Vy A. Vo, Juan Pablo Munoz, Theodore L. Willke, Tim Mattson, Ali Jannesari
Recently, language models (LMs), especially large language models (LLMs), have revolutionized the field of deep learning.
no code implementations • 28 Jan 2024 • Le Chen, Arijit Bhattacharjee, Nesreen Ahmed, Niranjan Hasabnis, Gal Oren, Vy Vo, Ali Jannesari
Our extensive evaluations demonstrate that OMPGPT outperforms existing large language models specialized in OpenMP tasks and maintains a notably smaller size, aligning it more closely with the typical hardware constraints of HPC environments.
1 code implementation • 29 Dec 2023 • Waqwoya Abebe, Pablo Munoz, Ali Jannesari
This enables the server to perform stratified client sampling across clusters in every round.
no code implementations • 11 Nov 2023 • Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, Ali Jannesari
The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.
no code implementations • 6 Oct 2023 • Quazi Ishtiaque Mahmud, Ali TehraniJamsaz, Hung D Phan, Nesreen K. Ahmed, Ali Jannesari
Parallelizing sequentially written programs is a challenging task.
no code implementations • 30 Sep 2023 • Sixing Yu, J. Pablo Muñoz, Ali Jannesari
This is evident across tasks in both natural language processing and computer vision domains.
no code implementations • 9 Aug 2023 • Hung Phan, Ali Jannesari
Our NMT models of learning ASTTrans Representation can boost the Mean Reciprocal Rank of these state-of-the-art code search processes by up to 3. 08% and improve 23. 08% of queries' results over the CAT benchmark.
1 code implementation • NeurIPS 2023 • Ali TehraniJamsaz, Quazi Ishtiaque Mahmud, Le Chen, Nesreen K. Ahmed, Ali Jannesari
The remarkable growth and significant success of machine learning have expanded its applications into programming languages and program analysis.
no code implementations • 19 May 2023 • Sixing Yu, J. Pablo Muñoz, Ali Jannesari
Foundation Models (FMs), such as LLaMA, BERT, GPT, ViT, and CLIP, have demonstrated remarkable success in a wide range of applications, driven by their ability to leverage vast amounts of data for pre-training.
no code implementations • 9 May 2023 • Le Chen, Quazi Ishtiaque Mahmud, Hung Phan, Nesreen K. Ahmed, Ali Jannesari
However, applying machine learning techniques to parallelism detection presents several challenges, such as the lack of an adequate dataset for training, an effective code representation with rich information, and a suitable machine learning model to learn the latent features of code for diverse analyses.
no code implementations • 1 May 2023 • Arushi Sharma, Zefu Hu, Christopher Quinn, Ali Jannesari
This approach helps us understand which neurons and layers can be eliminated (redundancy analysis) and where important code properties are located within the network (concept analysis).
no code implementations • 25 Apr 2023 • Akash Dutta, Jordi Alcaraz, Ali TehraniJamsaz, Eduardo Cesar, Anna Sikora, Ali Jannesari
There is, thus, a need for a general purpose and efficient tuning approach that can be easily scaled and adapted to various tuning tasks.
no code implementations • 7 Apr 2023 • Ali TehraniJamsaz, Alok Mishra, Akash Dutta, Abid M. Malik, Barbara Chapman, Ali Jannesari
However, even with OpenMP, the developer must choose from among many strategies for exploiting a GPU or a CPU.
no code implementations • 22 Feb 2023 • Akash Dutta, Jee Choi, Ali Jannesari
Our approach identifies OpenMP configurations at different power constraints that yield a geometric mean performance improvement of more than $25\%$ and $13\%$ over the default OpenMP configuration on a 32-core Skylake and a $16$-core Haswell processor respectively.
no code implementations • 25 Jan 2023 • Aishwarya Sarkar, Chaoqun Lu, Ali Jannesari
We perform extensive experiments on a dataset of 23 watersheds in a northern state of the U. S. and present our findings.
no code implementations • 16 Dec 2022 • Waqwoya Abebe, Ali Jannesari
In this paper, we demonstrate the advantages of constructing a proxy-based locally heterogeneous DL topology to enhance convergence and maintain data privacy.
no code implementations • 9 Nov 2022 • Sixing Yu, J. Pablo Muñoz, Ali Jannesari
To address these challenges, we propose Resource-aware Federated Learning (RaFL).
no code implementations • 16 Aug 2022 • Duy Phuong Nguyen, Sixing Yu, J. Pablo Muñoz, Ali Jannesari
This method allows efficient multi-model knowledge fusion and the deployment of resource-aware models while preserving model heterogeneity.
no code implementations • 22 Jun 2022 • Hung Phan, Ali Jannesari
For time performance, we achieve about 570 seconds as the time performance in both three processes: node embedding initialization, model construction, and story point estimation.
no code implementations • 6 Mar 2022 • Hung Phan, Ali Jannesari
In this paper, we show the potential and possible challenges of Graph Neural Network text classification in story point level estimation.
no code implementations • 1 Mar 2022 • Ali TehraniJamsaz, Mihail Popov, Akash Dutta, Emmanuelle Saillard, Ali Jannesari
This paper demonstrates how the static Intermediate Representation (IR) of the code can guide NUMA/prefetcher optimizations without the prohibitive cost of performance profiling.
no code implementations • 1 Dec 2021 • Jansel Herrera-Gerena, Ramakrishnan Sundareswaran, John Just, Matthew Darr, Ali Jannesari
Learning effective visual representations without human supervision is a long-standing problem in computer vision.
1 code implementation • 29 Nov 2021 • Sixing Yu, Phuong Nguyen, Waqwoya Abebe, Wei Qian, Ali Anwar, Ali Jannesari
Federated learning~(FL) facilitates the training and deploying AI models on edge devices.
no code implementations • NeurIPS Workshop AI4Scien 2021 • Aishwarya Sarkar, Jien Zhang, Chaoqun Lu, Ali Jannesari
Extracting and meticulously analyzing geo-spatiotemporal features is crucial to recognize intricate underlying causes of natural events, such as floods.
no code implementations • 26 Sep 2021 • Ramakrishnan Sundareswaran, Jansel Herrera-Gerena, John Just, Ali Jannesari
Unsupervised disentangled representation learning is a long-standing problem in computer vision.
1 code implementation • 5 Sep 2021 • Deepak George Thomas, Tichakorn Wongpiromsarn, Ali Jannesari
The function approximators employed by traditional image-based Deep Reinforcement Learning (DRL) algorithms usually lack a temporal learning component and instead focus on learning the spatial component.
no code implementations • 13 Jun 2021 • Sixing Yu, Phuong Nguyen, Ali Anwar, Ali Jannesari
Our approach reduces up to 50\% FLOPs inference of DNNs on edge devices while maintaining the model's quality.
no code implementations • 25 May 2021 • Deepak-George Thomas, Daniil Olshanskyi, Karter Krueger, Tichakorn Wongpiromsarn, Ali Jannesari
The significant components of any successful autonomous flight system are task completion and collision avoidance.
no code implementations • 11 Mar 2021 • Jeremy Roghair, Kyungtae Ko, Amir Ehsan Niaraki Asli, Ali Jannesari
An important part focuses on obstacle detection and avoidance for UAVs navigating through an environment.
1 code implementation • 5 Feb 2021 • Sixing Yu, Arya Mazaheri, Ali Jannesari
Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources.
no code implementations • ICCV 2021 • Sixing Yu, Arya Mazaheri, Ali Jannesari
We compared our method with rule-based DNN embedding model compression methods to show the effectiveness of our method.
no code implementations • 9 Oct 2020 • Aishwarya Sarkar, Jien Zhang, Chaoqun Lu, Ali Jannesari
Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low.
no code implementations • 20 Aug 2020 • Rahim Mammadli, Ali Jannesari, Felix Wolf
Provided with sub-sequences constituting LLVM's O3 sequence, our agent learns to outperform the O3 sequence on the set of source codes used for training and achieves competitive performance on the validation set, gaining up to 1. 32x speedup on previously-unseen programs.
1 code implementation • 26 Sep 2019 • Amir Niaraki, Jeremy Roghair, Ali Jannesari
During an exploration task with sparsely distributed goals and within a UAV's battery life, the proposed architecture could detect more than twice the amount of goal objects compared to the coverage path planning algorithm in moderate wind field.
no code implementations • 14 Jul 2019 • Venkatesh Theru Mohan, Ali Jannesari
Deep learning had been used in program analysis for the prediction of hidden software defects using software defect datasets, security vulnerabilities using generative adversarial networks as well as identifying syntax errors by learning a trained neural machine translation on program codes.
no code implementations • 30 May 2019 • Subrahmanyam Vaddi, Chandan Kumar, Ali Jannesari
We propose a deep feature pyramid architecture which makes use of inherent properties of features extracted from Convolutional Networks by capturing more generic features in the images (such as edge, color etc.)
no code implementations • 21 Nov 2016 • Matthew W. Moskewicz, Ali Jannesari, Kurt Keutzer
On Qualcomm GPUs, we show that our framework enables productive development of target-specific optimizations, and achieves reasonable absolute performance.