1 code implementation • 28 Mar 2024 • Mohsen Gholami, Mohammad Akbari, Cindy Hu, Vaden Masrani, Z. Jane Wang, Yong Zhang
Knowledge distillation from LLMs is essential for the efficient deployment of language models.
no code implementations • 7 Feb 2024 • Marek Klemes, Lan Hu, Greg Bowles, Mohammad Akbari, Soulideth Thirakoune, Michael Schwartzman, Kevin Zhang, Tan Huy Ho, David Wessel, Wen Tong
The OAM beams have a helical phase and polarization structure and have conical amplitude shape in the far field.
no code implementations • 26 Oct 2023 • Mohammad Akbari, Saeed Ranjbar Alvar, Behnam Kamranian, Amin Banitalebi-Dehkordi, Yong Zhang
Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages.
1 code implementation • journal 2023 • Mehdi Paykan Heyrati, Zahra Ghorbanali, Mohammad Akbari, Ghasem Pishgahi, and Fatemeh Zare-Mirakabad
In particular, we introduce a novel representation for the bioactivity classes, called Bio-Prof, and enhance the original bioactivity data sets to tackle data scarcity.
Ranked #1 on Molecular Property Prediction on Tox21
1 code implementation • ICCV 2023 • Mohsen Gholami, Mohammad Akbari, Xinglu Wang, Behnam Kamranian, Yong Zhang
This is the first work that proposes transferability estimation for object detection task.
Ranked #1 on Transferability on classification benchmark
1 code implementation • 29 Jul 2023 • Mohammadali Sefidi Esfahani, Mohammad Akbari
Social platforms have emerged as crucial platforms for disseminating information and discussing real-life social events, offering researchers an excellent opportunity to design and implement novel event detection frameworks.
2 code implementations • 1 Mar 2023 • Masoud Akbari, Amir Hossein Karimi, Tayyebeh Saeedi, Zeinab Saeidi, Kiana Ghezelbash, Fatemeh Shamsezat, Mohammad Akbari, Ali Mohades
To evaluate the effectiveness of our benchmark, we employ state-of-the-art methods for intent detection and slot filling.
no code implementations • 7 Apr 2022 • Elaheh Vaezpour, Layla Majzoobi, Mohammad Akbari, Saeedeh Parsaeefard, Halim Yanikomeroglu
Cell outage compensation enables a network to react to a catastrophic cell failure quickly and serve users in the outage zone uninterruptedly.
no code implementations • ACL 2022 • Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
As such, it can be applied to black-box pre-trained models without a need for architectural manipulations, reassembling of modules, or re-training.
no code implementations • 29 Dec 2021 • Arian Sabaghi, Marzieh Oghbaie, Kooshan Hashemifard, Mohammad Akbari
Hence, a new research area dealing with the development of more generalized as well as accurate models is increasingly attracting the attention of the research community and industry.
1 code implementation • 20 Oct 2021 • Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one.
no code implementations • 15 Oct 2021 • Marzieh Oghbaie, Arian Sabaghi, Kooshan Hashemifard, Mohammad Akbari
Driven by deep learning techniques and large-scale datasets, recent years have witnessed a paradigm shift in automatic lip reading.
no code implementations • 12 Aug 2021 • Mahsan Abdoli, Mohammad Akbari, Jamal Shahrabi
The obtained results from our experiments on the benchmark and real-life credit scoring datasets illustrate the robustness and effectiveness of the Bagging Supervised Autoencoder Classifier in the classification of loan applicants that can be regarded as a positive development in credit scoring models.
1 code implementation • 14 Jul 2021 • Haisheng Fu, Feng Liang, Jianping Lin, Bing Li, Mohammad Akbari, Jie Liang, Guohe Zhang, Dong Liu, Chengjie Tu, Jingning Han
However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image.
no code implementations • 10 May 2021 • Mohammad Akbari, Mohammad Reza Abedi, Roghayeh Joda, Mohsen Pourghasemian, Nader Mokari, Melike Erol-Kantarci
In this paper, we first utilize single agent low-complex compound action actor-critic RL to cover both discrete and continuous actions and jointly minimize VNF cost and AoI in terms of network resources under end-to end Quality of Service constraints.
no code implementations • 12 Jan 2021 • Seyedkooshan Hashemifard, Mohammad Akbari
Despite the results each of these techniques has achieved for a certain attack scenario or dataset, most of them still failed to generalized the problem for unseen conditions, as the efficiency of each is limited to certain type of presentation attacks and instruments (PAI).
no code implementations • 31 Dec 2020 • Mohammad Akbari, Jie Liang, Jingning Han, Chengjie Tu
Recently deep learning-based image compression has shown the potential to outperform traditional codecs.
no code implementations • 30 Nov 2020 • Sepideh Bazzaz Abkenar, Mostafa Haghi Kashani, Mohammad Akbari, Ebrahim Mahdipour
Literature review analysis reveals that most of the existing methods rely on Machine Learning-based algorithms.
1 code implementation • 18 Oct 2020 • Mahsan Abdoli, Mohammad Akbari, Jamal Shahrabi
Automatic credit scoring, which assesses the probability of default by loan applicants, plays a vital role in peer-to-peer lending platforms to reduce the risk of lenders.
no code implementations • 16 Aug 2020 • Mahdi Nouri Boroujerdi, Mohammad Akbari, Roghayeh Joda, Mohammad Ali Maddah-Ali, Babak Hossein Khalaj
In this paper, we employ deep reinforcement learning to develop a novel radio resource allocation and packet scheduling scheme for different Quality of Service (QoS) requirements applicable to LTEadvanced and 5G networks.
no code implementations • L4DC 2020 • Mohammad Akbari, Bahman Gharesifard, Tamas Linder
We study an online setting of the linear quadratic Gaussian optimal control problem on a sequence of cost functions, where similar to classical online optimization, the future decisions are made by only knowing the cost in hindsight.
1 code implementation • 24 Feb 2020 • Mohammad Akbari, Jie Liang, Jingning Han, Chengjie Tu
Learned image compression has recently shown the potential to outperform the standard codecs.
no code implementations • 26 Jan 2020 • Binglin Li, Mohammad Akbari, Jie Liang, Yang Wang
Recently many works attempt to develop image compression models based on deep learning architectures, where the uniform scalar quantizer (SQ) is commonly applied to the feature maps between the encoder and decoder.
no code implementations • 11 Dec 2019 • Mohammad Akbari, Jie Liang, Jingning Han, Chengjie Tu
Recently it has been shown that deep learning-based image compression has shown the potential to outperform traditional codecs.
no code implementations • 15 Sep 2019 • Shihao Zou, Zhonghua Li, Mohammad Akbari, Jun Wang, Peng Zhang
By defining reward as a function of NDCG, we can optimize our model directly on the ranking performance measure.
no code implementations • 24 Aug 2019 • Mohammad Akbari, Rumi Chunara
Person-generated data sources, such as actively contributed surveys as well as passively mined data from social media offer opportunity to capture such context, however the self-reported nature and sparsity of such data mean that such data are noisier and less specific than physiological measures such as blood glucose values themselves.
no code implementations • 15 Jul 2019 • Haisheng Fu, Feng Liang, Bo Lei, Nai Bian, Qian Zhang, Mohammad Akbari, Jie Liang, Chengjie Tu
Recently deep learning-based methods have been applied in image compression and achieved many promising results.
no code implementations • 1 Mar 2019 • Mostafa Rezazad, Matthias R. Brust, Mohammad Akbari, Pascal Bouvry, Ngai-Man Cheung
A novel class of extreme link-flooding DDoS (Distributed Denial of Service) attacks is designed to cut off entire geographical areas such as cities and even countries from the Internet by simultaneously targeting a selected set of network links.
no code implementations • 3 Dec 2018 • Mohammad Akbari, Kunal Relia, Anas Elghafari, Rumi Chunara
Online communities provide a unique way for individuals to access information from those in similar circumstances, which can be critical for health conditions that require daily and personalized management.
1 code implementation • 22 Oct 2018 • Alberto Cetoli, Mohammad Akbari, Stefano Bragaglia, Andrew D. O'Harney, Marc Sloan
We tackle \ac{NED} by comparing entities in short sentences with \wikidata{} graphs.
2 code implementations • 8 Jun 2018 • Mohammad Akbari, Jie Liang, Jingning Han
A compact representation of the input image is also generated and encoded as the first enhancement layer.
1 code implementation • 1 Jun 2018 • Mohammad Akbari, Jie Liang
A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced.