Navid Azizan

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.

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 ...

Haoyuan Sun will present "On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning" arxiv.org/abs/2501.18187

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 ...

Andrea Goertzen and Sunbochen Tang will present "ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees" arxiv.org/abs/2512.01984

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...

Youngjae Min will present "HardNet: Hard-Constrained Neural Networks" arxiv.org/abs/2410.10807

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...

Kaveh Alim will present "Activation-Informed Merging of Large Language Models" arxiv.org/abs/2502.02421

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...

Young-Jin Park will present "Know What You Don't Know: Uncertainty Calibration of Process Reward Models" arxiv.org/abs/2506.09338

Excited to be at #NeurIPS with several of my brilliant students! Some of them are looking for internships and full-time roles, and we are also recruiting new students and postdocs—come find us at any of these sessions!

#NeurIPS2025

Introducing Instance-Adaptive Inference-Time Scaling!

Paper: arxiv.org/abs/2506.09338
Code: github.com/azizanlab/in...

Congratulations, Necmiye!