activity
20242026
collaborators

10 papers

cs.DS2026

Context Compaction Theory

Hayder Tirmazi, Sam Markelon, Allison Bishop +1

Large Language Models (LLMs) have a bounded context window. The context window is the maximum input size an LLM can consume for a single inference. AI agents rely on a process call…

cs.AR2026

DRCY: Agentic Hardware Design Reviews

Kyle Dumont, Nicholas Herbert, Hayder Tirmazi +1

Hardware design errors discovered after fabrication require costly physical respins that can delay products by months. Existing electronic design automation (EDA) tools enforce str…

cs.AI2026

Orla: A Library for Serving LLM-Based Multi-Agent Systems

Rana Shahout, Hayder Tirmazi, Minlan Yu +1

We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multiple LLM inference steps, too…

cs.CR2025

Whistledown: Combining User-Level Privacy with Conversational Coherence in LLMs

Chelsea McMurray, Hayder Tirmazi

Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can co…

cs.CR2025

Adversary Resilient Learned Bloom Filters

Ghada Almashaqbeh, Allison Bishop, Hayder Tirmazi

A learned Bloom filter (LBF) combines a classical Bloom filter (CBF) with a learning model to reduce the amount of memory needed to represent a given set while achieving a target f…

cs.CR2025

All Proof of Work But No Proof of Play

Hayder Tirmazi

Speedrunning is a competition that emerged from communities of early video games such as Doom (1993). Speedrunners try to finish a game in minimal time. Provably verifying the auth…