activity
20242026
collaborators

6 papers

cs.LG2026

Tapered Language Models

Reza Bayat, Ali Behrouz, Aaron Courville

Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly…

cs.CL2025

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Sangmin Bae, Yujin Kim, Reza Bayat +8

Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency effo…

cs.LG2025

Steering Large Language Model Activations in Sparse Spaces

Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki +2

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations dur…

cs.LG2024

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones

Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas +2

Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty. The approach enables pred…

cs.LG2024

The Pitfalls of Memorization: When Memorization Hurts Generalization

Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob +2

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor gener…

cs.CV2024

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques

Rishika Bhagwatkar, Shravan Nayak, Reza Bayat +4

Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they are becoming increasingly prevalent, ensuring their robustness a…