12 citations · 13 across the 5 of their papers we have counts for
5 papers
Data-Aware Random Feature Kernel for Transformers
Amirhossein Farzam, Hossein Mobahi, Nolan Andrew Miller +1
Transformers excel across domains, yet their quadratic attention complexity poses a barrier to scaling. Random-feature attention, as in Performers, can reduce this cost to linear i…
Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
Amirhossein Farzam, Majid Behabahani, Mani Malek +2
Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particu…
SPOT: Sparsification with Attention Dynamics via Token Relevance in Vision Transformers
Oded Schlesinger, Amirhossein Farzam, J. Matias Di Martino +1
While Vision Transformers (ViT) have demonstrated remarkable performance across diverse tasks, their computational demands are substantial, scaling quadratically with the number of…
Multi-Task Learning Improves Performance In Deep Argument Mining Models
Amirhossein Farzam, Shashank Shekhar, Isaac Mehlhaff +1
The successful analysis of argumentative techniques from user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools…
Opinion Manipulation on Farsi Twitter
Amirhossein Farzam, Parham Moradi, Saeedeh Mohammadi +2
For Iranians and the Iranian diaspora, the Farsi Twittersphere provides an important alternative to state media and an outlet for political discourse. But this understudied online…