Navid Azizan
@navidazizan.bsky.social
MIT Prof | AI & machine learning, systems & control, optimization | Fmr postdoc @Stanford, PhD @Caltech
azizan.mit.edu
azizan.mit.edu
Huge thanks to our amazing co-authors and collaborators—Kristjan Greenewald, Hao Wang, Amin Heyrani Nobari, Ali ArjomandBigdeli, Akash Srivastava, Faez Ahmed, Ali Jadbabaie, Ji Young Byun, and Rama Chellappa—and to MIT-IBM Watson AI Lab, Google, Amazon, and MathWorks for their support.
December 5, 2025 at 3:29 AM
Huge thanks to our amazing co-authors and collaborators—Kristjan Greenewald, Hao Wang, Amin Heyrani Nobari, Ali ArjomandBigdeli, Akash Srivastava, Faez Ahmed, Ali Jadbabaie, Ji Young Byun, and Rama Chellappa—and to MIT-IBM Watson AI Lab, Google, Amazon, and MathWorks for their support.
Haoyuan Sun will present "On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning" arxiv.org/abs/2501.18187
On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates. Recent research has ...
arxiv.org
December 5, 2025 at 3:29 AM
Haoyuan Sun will present "On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning" arxiv.org/abs/2501.18187
Andrea Goertzen and Sunbochen Tang will present "ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees" arxiv.org/abs/2512.01984
ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees
Chaos is a fundamental feature of many complex dynamical systems, including weather systems and fluid turbulence. These systems are inherently difficult to predict due to their extreme sensitivity to ...
arxiv.org
December 5, 2025 at 3:29 AM
Andrea Goertzen and Sunbochen Tang will present "ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees" arxiv.org/abs/2512.01984
Youngjae Min will present "HardNet: Hard-Constrained Neural Networks" arxiv.org/abs/2410.10807
HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
Incorporating prior knowledge or specifications of input-output relationships into machine learning models has attracted significant attention, as it enhances generalization from limited data and yiel...
arxiv.org
December 5, 2025 at 3:29 AM
Youngjae Min will present "HardNet: Hard-Constrained Neural Networks" arxiv.org/abs/2410.10807
Kaveh Alim will present "Activation-Informed Merging of Large Language Models" arxiv.org/abs/2502.02421
Activation-Informed Merging of Large Language Models
Model merging, a method that combines the parameters and embeddings of multiple fine-tuned large language models (LLMs), offers a promising approach to enhance model performance across various tasks w...
arxiv.org
December 5, 2025 at 3:29 AM
Kaveh Alim will present "Activation-Informed Merging of Large Language Models" arxiv.org/abs/2502.02421
Young-Jin Park will present "Know What You Don't Know: Uncertainty Calibration of Process Reward Models" arxiv.org/abs/2506.09338
Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibr...
arxiv.org
December 5, 2025 at 3:29 AM
Young-Jin Park will present "Know What You Don't Know: Uncertainty Calibration of Process Reward Models" arxiv.org/abs/2506.09338
Congratulations, Necmiye!
May 21, 2025 at 11:36 PM
Congratulations, Necmiye!