5 papers
On Locality and Length Generalization in Visual Reasoning
Pulkit Madan, Sanjay Haresh, Reza Ebrahimi +3
A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes…
AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety
Yanjing Ren, Reza Ebrahimi, TengTeng Ma
As AI companion platforms such as Replika and Character.AI rapidly grow, concerns about unsafe human-AI interactions have intensified. This study introduces AICompanionBench, to ou…
Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy
Rouzbeh Behnia, Jeremiah Birrell, Arman Riasi +3
Federated learning (FL) enables organizations to collaboratively train models without sharing their datasets. Despite this advantage, recent studies show that both client updates a…
Delayed Attention Training Improves Length Generalization in Transformer--RNN Hybrids
Buu Phan, Reza Ebrahimi, Sanjay Haresh +1
We study length generalization in sequence models on a composite problem involving both state tracking and associative recall. Prior work finds that recurrent networks handle state…
Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels
Jeremiah Birrell, Reza Ebrahimi
We introduce ANTIDOTE, a new class of objectives for learning under noisy labels which are defined in terms of a relaxation over an information-divergence neighborhood. Using conve…