10 citations · 17 across the 11 of their papers we have counts for
11 papers
Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes
Justin Bauer, Thomas Walshe, Derek Pham +4
Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Rei…
The Hitchhikers Guide to Rubric Quality Understanding and Enrichment
Zhengyang Qi, Ankit Aich, Charles Dickens +7
Rubrics distill notions of expert quality and measure agent performance. However, the quality of rubrics themselves have not been systematically measured and are often left to down…
Automating Benchmark Design
Amanda Dsouza, Harit Vishwakarma, Zhengyang Qi +6
The rapid progress and widespread deployment of LLMs and LLM-powered agents has outpaced our ability to evaluate them. Hand-crafted, static benchmarks are the primary tool for asse…
TrajPRed: Trajectory Prediction with Region-based Relation Learning
Chen Zhou, Ghassan AlRegib, Armin Parchami +1
Forecasting human trajectories in traffic scenes is critical for safety within mixed or fully autonomous systems. Human future trajectories are driven by two major stimuli, social…
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within Datasets
Shubham Shrivastava, Xianling Zhang, Sushruth Nagesh +1
Data imbalance is a well-known issue in the field of machine learning, attributable to the cost of data collection, the difficulty of labeling, and the geographical distribution of…
Exploiting the Distortion-Semantic Interaction in Fisheye Data
Kiran Kokilepersaud, Mohit Prabhushankar, Yavuz Yarici +2
In this work, we present a methodology to shape a fisheye-specific representation space that reflects the interaction between distortion and semantic context present in this data m…
Learning Trajectory-Conditioned Relations to Predict Pedestrian Crossing Behavior
Chen Zhou, Ghassan AlRegib, Armin Parchami +1
In smart transportation, intelligent systems avoid potential collisions by predicting the intent of traffic agents, especially pedestrians. Pedestrian intent, defined as future act…
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
Abhinav Kumar, Garrick Brazil, Enrique Corona +2
Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D…
Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras
Zhengxia Zou, Rusheng Zhang, Shengyin Shen +4
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infras…
Localization of a Smart Infrastructure Fisheye Camera in a Prior Map for Autonomous Vehicles
Subodh Mishra, Armin Parchami, Enrique Corona +4
This work presents a technique for localization of a smart infrastructure node, consisting of a fisheye camera, in a prior map. These cameras can detect objects that are outside th…
Infrastructure Node-based Vehicle Localization for Autonomous Driving
Elijah S. Lee, Ankit Vora, Armin Parchami +3
Vehicle localization is essential for autonomous vehicle (AV) navigation and Advanced Driver Assistance Systems (ADAS). Accurate vehicle localization is often achieved via expensiv…