10 papers
Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents
Sina Hajimiri, Masih Aminbeidokhti, Jose Dolz +4
Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely r…
Distilling Specialized Orders for Visual Generation
Rishav Pramanik, Amin Sghaier, Masih Aminbeidokhti +6
Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Typical AR models are locked onto…
How (Mis)calibrated is Your Federated CLIP and What To Do About It?
Mainak Singha, Masih Aminbeidokhti, Paolo Casari +3
While vision-language models like CLIP have been extensively studied, their calibration, crucial for reliable predictions, has received limited attention. Although a few prior work…
LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
Masih Aminbeidokhti, Subhankar Roy, Eric Granger +2
Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows…
Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?
Srikanth Muralidharan, Heitor R. Medeiros, Masih Aminbeidokhti +2
Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with…
WiSE-OD: Benchmarking Robustness in Infrared Object Detection
Heitor R. Medeiros, Atif Belal, Masih Aminbeidokhti +2
Object detection (OD) in infrared (IR) imagery is critical for low-light and nighttime applications. However, the scarcity of large-scale IR datasets forces models to rely on weigh…