Corporate Talk




Yixin Hu

(Senior Graphics Researcher at Pixel Labs)

Bio: Yixin Hu is now a senior Graphics Researcher at Pixel Lab, Tencent America. She obtained her doctoral degree from Courant Institute of Mathematical Sciences, New York University where she joined Geometric Computing Lab and started working with professor Daniele Panozzo. Her research interests are Computer Graphics and 3D Geometry Processing. Her research has been recognized by Adobe Research Fellowship (2019), Jacob T. Schwartz Ph.D. Fellowship (2019), and Sandra Bleistein Prize (2021).

Title for Talk: WildMeshing: Unstructured Mesh Generation and Repairing in the Wild

Abstract:  WildMeshing is a series of meshing algorithms I proposed during my PhD, which solved a long-standing yet fundamental problem in Geometry Processing: generating high-quality triangle/tetrahedral meshes and repairing imperfect geometries robustly and automatically. WildMeshing has been tested on over ten thousand real-world inputs and achieved a 100% success rate. The implementation of WildMeshing is open-source and is currently used in the released products of companies like nToppology, AREVO, Mechanical Finder, and Rhino3D.  WildMeshing can also be used as a black-box for generating large collections of clean geometries for geometric deep learning.

Sophia Paleologou


Bio: Sophia Paleologou is a seasoned IT executive with over 20 years of experience developing software platforms for a wide spectrum of applications. She has been an integral part of the design and development of several large, enterprise-grade commercial products. She is currently the Chief Technology Officer of UNS, an identity and access management solution provider. Sophia holds a BS in
Mathematics from the University of Athens, Greece and a PhD in Computer Science from Yale University. She has also co-authored multiple patents in Cryptography and Error Correction.

Title for Talk: Enabling Better Medical Research through Privacy-Preserving Record Linking

Abstract: The outcomes of medical research heavily rely on the quality of the data it is based on. Although healthcare providers collect a vast amount of good-quality medical data, they
are severely restricted in how they can share this data because of existing privacy regulations. Before patient data can be shared for research purposes, it has to be
stripped from all information that could potentially be used to identify the associated patients. Once personal identifiable information (PII) is stripped, linking of medical data
across healthcare providers becomes very challenging. In this work, we present a solution that uses a new cryptographic primitive to facilitate linking of medical data without using PII. We also present an implementation of our novel solution over a network of security nodes that further bolsters the security and privacy characteristics of our solution as well as the results of a series of pilot tests engaging with a small number of providers and a state registry that explore potential integration and adoption challenges.

Roberto Calandra

(Research Scientist at Facebook AI Research)

Bio: Roberto Calandra is a Research Scientist at Meta AI (formerly Facebook AI Research). Previously, he was a Postdoctoral Scholar at the University of California, Berkeley (US) in the Berkeley Artificial Intelligence Research Laboratory (BAIR). His education includes a Ph.D. from TU Darmstadt (Germany), a M.Sc. in Machine Learning and Data Mining from the Aalto university (Finland), and a B.Sc. in Computer Science from the Università degli studi di Palermo (Italy). His scientific interests are broadly at the conjunction of Decision-making, Robotics and Machine Learning. He served the scientific community, among other, by being Program Chair for AISTATS 2020, Guest Editor for JMLR, and co-organizing over 17 workshops at international conferences (NeurIPS, ICML, ICLR, ICRA, IROS, RSS). He also led the development of DIGIT -- the first commercial compact high-resolution tactile sensor.

Title for Talk: Towards Digital Touch Sensing

Abstract:  Touch is a crucial sensor modality in both humans and robots. Recent advances in tactile sensing hardware have resulted -- for the first time -- in the availability of mass-produced, high-resolution, inexpensive, and reliable tactile sensors. In this talk, I will talk about the opportunities created by the availability of this hardware, towards the digitalization of touch as a sensing modality. Following, I will argue for the importance of creating a new computational field of "Touch processing" dedicated to the processing and understanding of touch, similarly to what computer vision is for vision. This new field will present significant challenges both in terms of research and engineering, but also new exciting opportunities in a wide range of real-world applications.


Important Deadlines

Full Paper Submission:23rd September 2022
Acceptance Notification: 12th October 2022
Final Paper Submission:20th October 2022
Early Bird Registration
20th October 2022
Presentation Submission: 20th October 2022
Conference: 26 - 29 October 2022

Previous Conference


Sister Conferences







Generic selectors
Exact matches only
Search in title
Search in content
Post Type Selectors
Filter by Categories




• Best Paper Award will be given for each track.

• Conference Record No 54665