publight

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar
PDF Techcrunch Hackernews
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Sachin Mehta, Mohammad Sekhavat, Qingqing Cao, Max Horton, Yanzi Jin, Frank Sun, Iman Mirzadeh, Mahyar Najibikohnehshahri, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari
PDF Code Huggingface The Verge VentureBeat
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024
Keivan Alizadeh, Iman Mirzadeh, Dmitry Belenko, Karen Khatamifard, Minsik Cho, Carlo C Del Mundo, Mohammad Rastegari, Mehrdad Farajtabar
PDF Hackernews Financial Times
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
International Conference on Learning Representations (ICLR), 2024 [Oral]
Iman Mirzadeh, Keivan Alizadeh-Vahid, Sachin Mehta, Carlo C Del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
PDF Cite Poster Slides
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Wide Neural Networks Forget Less Catastrophically
International Conference on Machine Learning (ICML), 2022
Iman Mirzadeh, Arslan Chaudhry, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
PDF Cite
Wide Neural Networks Forget Less Catastrophically
Linear Mode Connectivity in Multitask and Continual Learning
International Conference on Learning Representations (ICLR), 2021
Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh
PDF Cite Code Video
Linear Mode Connectivity in Multitask and Continual Learning
Understanding the Role of Training Regimes in Continual Learning
Advances in Neural Information Processing Systems (NeurIPS), 2020
The abstract version presented at ICML 2020 Workshop on Continual Learning
Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh
PDF Cite Code Slides Video
Understanding the Role of Training Regimes in Continual Learning
Dropout as an Implicit Gating Mechanism For Continual Learning
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020
Runner-up award at CVPR'20 Workshop on Continual Learning in Computer Vision
Iman Mirzadeh, Mehrdad Farajtabar, Hassan Ghasemzadeh
PDF Cite Code Video
Dropout as an Implicit Gating Mechanism For Continual Learning
Optimal Policy for Deployment of Machine Learning Models on Energy-Bounded Systems
International Joint Conference on Artificial Intelligence (IJCAI), 2020
Iman Mirzadeh, Hassan Ghasemzadeh
PDF Cite
Optimal Policy for Deployment of Machine Learning Models on Energy-Bounded Systems
Improved Knowledge Distillation via Teacher Assistant
AAI Conference on Artificial Intelligence (AAAI), 2020
Iman Mirzadeh, Mehrdad Farajtabar, Ang Li, Nir Levine, Akihiro Matsukawa, Hassan Ghasemzadeh
PDF Code Video
Improved Knowledge Distillation via Teacher Assistant