3 citations · 6 across the 10 of their papers we have counts for
5 papers · 1 filter
Dynamic Minimax Regret Optimization for Robust LLM Post-Training
Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan +3
Modern LLM training increasingly relies on heterogeneous data sources spanning different domains, tasks, preference distributions, and difficulty levels. We study dynamic minimax r…
ASTRA: Low-Overhead Runtime Architecture for STReam Adaptation in Video Analytics
Mahshid Ghasemi, Zoran Kostic, Javad Ghaderi +1
Real-time video analytics is crucial for smart city applications and cloud-connected vehicle control. To improve analytics accuracy, it is desirable to process the video at the hig…
Denial of Deadline: Network-Driven Accuracy Collapse in Distributed Inference Pipelines
Jhonatan Tavori, Gur-Eyal Sela, Ion Stoica +1
Inference systems increasingly combine a fast path that returns predictions within the application's latency deadline together with a higher-accuracy slow path that runs higher-com…
Multi-Pedestrian Safety Warning at Urban Intersections Use Case of Digital Twin
Yongjie Fu, Qi Gao, Mahshid Ghasemi Dehkordi +2
Digital twins (DTs) for urban transportation systems have gained increasing attention; however, their systematic evaluation in safety-critical scenarios remains limited. This paper…
A Vision-Based Analysis of Congestion Pricing in New York City
Mehmet Kerem Turkcan, Jhonatan Tavori, Javad Ghaderi +3
We examine the impact of New York City's congestion pricing program through automated analysis of traffic camera data. Our computer vision pipeline processes footage from over 900…