6 papers
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…
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…
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…
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…
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…
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…