Publications (7)
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…
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…
: 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.…
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…
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…
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…
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…