Publications (8)
ProToken: Token-Level Attribution for Federated Large Language Models
Waris Gill, Ahmad Humayun, Ali Anwar +1
Federated Learning (FL) enables collaborative training of Large Language Models (LLMs) across distributed data sources while preserving privacy. However, when federated LLMs are de…
Iterative Machine Teaching
Weiyang Liu, Bo Dai, Ahmad Humayun +5
In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch a…
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
Joseph Ortiz, Antoine Dedieu, Wolfgang Lehrach +7
Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for ex…
Operationalizing Property-Based Testing for Data-Intensive Scalable Computing Systems
Yaoxuan Wu, Ingrid Lee, Ahmad Humayun +2
While fuzzing effectively catches crashes, its shallow oracles often miss semantic drifts and optimization-related errors in data-intensive scalable computing (DISC) frameworks. Pr…
PALM: Path-aware LLM-based Test Generation with Comprehension
Yaoxuan Wu, Xiaojie Zhou, Ahmad Humayun +2
Symbolic execution is a widely used technique for test generation, offering systematic exploration of program paths through constraint solving. However, it is fundamentally constra…
Low-shot Object Learning with Mutual Exclusivity Bias
Anh Thai, Ahmad Humayun, Stefan Stojanov +3
This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in in…
Finding Temporally Consistent Occlusion Boundaries in Videos using Geometric Context
S. Hussain Raza, Ahmad Humayun, Matthias Grundmann +2
We present an algorithm for finding temporally consistent occlusion boundaries in videos to support segmentation of dynamic scenes. We learn occlusion boundaries in a pairwise Mark…
Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models
Sabaat Haroon, Ahmad Faraz Khan, Ahmad Humayun +5
Generative Large Language Models (LLMs) are increasingly used in non-generative software maintenance tasks, such as fault localization (FL). Success in FL depends on a models abili…