Events

Upcoming events

Formal Synthesis for Robots

Hadas Kress-Gazit Cornell University
25 May 2020, 4:00 pm - 5:00 pm
Kaiserslautern building G26, room online
SWS Distinguished Lecture Series
In this talk I will describe how formal methods such as synthesis – automatically creating a system from a formal specification – can be leveraged to design robots, explain and provide guarantees for their behavior, and even identify skills they might be missing. I will discuss the benefits and challenges of synthesis techniques and will give examples of different robotic systems including modular robots, swarms and robots interacting with people.

The (In)Security of Modern Communication: From Guesses to Guarantees

Cas Cremers CISPA
03 Jun 2020, 12:15 pm - 1:15 pm
Saarbrücken building E1 5, room 002
Joint Lecture Series
-

Internet Measurements: Evaluating Deployment and Security Practices

Oliver Gasser MPI-INF - D3
01 Jul 2020, 12:15 pm - 1:15 pm
Saarbrücken building E1 3, room HS 2
Joint Lecture Series
-

Recent events

CANCELLED: Computer Science Competitions @ SIC

Julian Baldus, Marian Dietz, Simon Schwarz Fachrichtung Informatik - Saarbrücken
01 Apr 2020, 12:15 pm - 1:15 pm
Saarbrücken building E2 2, room Günther-Hotz-HS
Joint Lecture Series
-

*Remote Talk* Improve Operations of Data Center Networks with Physical-Layer Programmability

Yiting Xia Facebook
26 Mar 2020, 10:00 am - 11:00 am
Saarbrücken building E1 5, room 029
simultaneous videocast to Kaiserslautern building G26, room 111 / Meeting ID: 6312
SWS Colloquium
Physical-layer programmability enables the network topology to be changed dynamically. In this talk, the speaker will make a case that cloud data center networks can be significantly easier to manage with physical-layer programmability. Three example network architectures will be shown as different use cases of this approach. ShareBackup enhances reliability through sharing backup switches efficiently network-wide, where a backup switch can be brought online instantaneously to recover from failures. Flat-tree solves the problem of choosing the right network topology for different cloud services by dynamically changing topological clustering characteristics of the network. …
Physical-layer programmability enables the network topology to be changed dynamically. In this talk, the speaker will make a case that cloud data center networks can be significantly easier to manage with physical-layer programmability. Three example network architectures will be shown as different use cases of this approach. ShareBackup enhances reliability through sharing backup switches efficiently network-wide, where a backup switch can be brought online instantaneously to recover from failures. Flat-tree solves the problem of choosing the right network topology for different cloud services by dynamically changing topological clustering characteristics of the network. OmniSwitch is a universal building block of data center networks that supports automatic device wiring and easy device maintenance. At the end of the talk, the speaker will briefly introduce an ongoing follow-up research that extends physical-layer programmability from data center networks to backbone networks.
Read more

*Remote Talk* Learning efficient representations for image and video understanding

Yannis Kalantidis Facebook AI
18 Mar 2020, 10:00 am - 11:00 am
Saarbrücken building E1 5, room 029
simultaneous videocast to Kaiserslautern building G26, room 111 / Meeting ID: 6312
SWS Colloquium
Two important challenges in image and video understanding are designing more efficient deep Convolutional Neural Networks and learning models that are able to achieve higher-level understanding. In this talk, I will present some of my recent works towards tackling these challenges. Specifically, I will introduce the Octave Convolution [ICCV 2019], a plug-and-play replacement for the convolution operator that exploits the spatial redundancy of CNN activations and can be used without any adjustments to the network architecture. …
Two important challenges in image and video understanding are designing more efficient deep Convolutional Neural Networks and learning models that are able to achieve higher-level understanding. In this talk, I will present some of my recent works towards tackling these challenges. Specifically, I will introduce the Octave Convolution [ICCV 2019], a plug-and-play replacement for the convolution operator that exploits the spatial redundancy of CNN activations and can be used without any adjustments to the network architecture. I will also present the Global Reasoning Networks [CVPR 2019], a new approach for reasoning over arbitrary sets of features of the input, by projecting them from a coordinate space into an interaction space where relational reasoning can be efficiently computed.  The two methods presented are complementary and achieve state-of-the-art performance on both image and video tasks. Aiming for higher-level understanding, I will also present our recent works on vision and language modeling, specifically our work on learning state-of-the-art image and video captioning models that are also able to better visually ground the generated sentences with [CVPR 2019] or without [arXiv 2019] explicit localization supervision. The talk will conclude with current research and a brief vision for the future.
Read more

Archive