Mehrdad Farajtabar
Artificial Intelligence · 2018–2025
A researcher in the Science corpus: 21 papers; trusts 2,063 researchers and is trusted by 122 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 816 citations into it; #2,991 of 36,961 by trust here, #2,683 by citations
- Computer Vision and Pattern Recognition — 528 citations into it; #3,961 of 21,973 by trust here, #2,499 by citations
- Meta & Continual Learning — 206 citations into it; #51 of 1,043 by trust here, #58 by citations
- Representation & Self-Supervised Learning — 160 citations into it
- Optimization & Training — 152 citations into it; #609 of 2,605 by trust here, #626 by citations
- Model Architectures — 101 citations into it
- Reinforcement Learning — 93 citations into it
- Efficiency & Compression — 83 citations into it; #477 of 1,273 by trust here, #436 by citations
Whom Mehrdad Farajtabar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Kaiming He
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- Marc'Aurelio Ranzato
- Arslan Chaudhry
- Karen Simonyan
Who trusts Mehrdad Farajtabar overall
- Seyed Iman Mirzadeh
- Thang Van Doan
- Nathan Kallus
- Liyuan Wang
- Ziyang Tang
- Dong Yin
- Gobinda Saha
- Krishnan Raghavan
- Masatoshi Uehara
- Huiyi Hu
Papers from Mehrdad Farajtabar's perspective
Ordered by how strongly the researchers Mehrdad Farajtabar trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- More Robust Doubly Robust Off-policy Evaluation (2018) — 294 citations
- Improved Knowledge Distillation via Teacher Assistant: Bridging the Gap Between Student and Teacher (2019) — 159 citations
- Orthogonal Gradient Descent for Continual Learning (2019) — 536 citations
- Self-Distillation Amplifies Regularization in Hilbert Space (2020) — 286 citations
- Improved Knowledge Distillation via Teacher Assistant (2019) — 1,428 citations
- Linear Mode Connectivity in Multitask and Continual Learning (2020) — 180 citations
- The Effectiveness of Memory Replay in Large Scale Continual Learning (2020) — 41 citations
- Understanding the Role of Training Regimes in Continual Learning (2020) — 278 citations
- Wide Neural Networks Forget Less Catastrophically (2021) — 88 citations
- Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint. (2020) — 44 citations
- Dropout as an Implicit Gating Mechanism For Continual Learning (2020) — 47 citations
- SOLA: Continual Learning with Second-Order Loss Approximation (2020) — 20 citations
- Architecture Matters in Continual Learning (2022) — 64 citations
- Task-agnostic Continual Learning with Hybrid Probabilistic Models (2021) — 24 citations
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity (2025) — 429 citations
- GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models (2024) — 590 citations
- Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement (2023) — 16 citations
- TiC-CLIP: Continual Training of CLIP Models (2023) — 52 citations
- Efficient Continual Learning Ensembles in Neural Network Subspaces (2022) — 7 citations
- Cross-View Policy Learning for Street Navigation (2019) — 37 citations