papers

Publications (7)

math.CO2001

Hamiltonian Paths in Cartesian Powers of Directed Cycles

David Austin, Heather Gavlas, Dave Witte

The vertex set of the kth cartesian power of a directed cycle of length m can be naturally identified with the set of k-tuples of integers modulo m. For any two vertices v and w of…

cs.CL2026

LLM Router: Rethinking Routing with Prefill Activations

Tanay Varshney, Annie Surla, Michelle Xu +5

LLMs often achieve similar average benchmark accuracies while exhibiting complementary strengths on different subsets of queries, suggesting that a router with query-specific model…

cs.CL2025

: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding

Cesare Spinoso-Di Piano, David Austin, Pablo Piantanida +1

Figurative language (e.g., irony, hyperbole, understatement) is ubiquitous in human communication, resulting in utterances where the literal and the intended meanings do not match.…

cs.CV2026

Intuitive Surgical SurgToolLoc and SurgVU Challenges Results: 2022-2025

Aneeq Zia, Max Berniker, Rogerio Garcia Nespolo +153

Robotic assisted (RA) surgery promises to transform surgical intervention. Intuitive Surgical is committed to fostering these changes and the machine learning models and algorithms…

math.NA2022

The Image Deblurring Problem: Matrices, Wavelets, and Multilevel Methods

David Austin, Malena I. Español, Mirjeta Pasha

The image deblurring problem consists of reconstructing images from blur and noise contaminated available data. In this AMS Notices article, we provide an overview of some well kno…

cs.CV2023

FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation

Zhiqi Li, Zhiding Yu, David Austin +4

This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous D…

cs.CV2019

Learning to Localize Temporal Events in Large-scale Video Data

Mikel Bober-Irizar, Miha Skalic, David Austin

We address temporal localization of events in large-scale video data, in the context of the Youtube-8M Segments dataset. This emerging field within video recognition can enable app…