Colloquium Talks

March 22, 2023

April 7 Colloquium: "User Control in Adaptive Information Access"

Combining the decision power or AI with the ability of the user to guide and control it brings together the strong sides of artificial and human intelligence and could lead to better results. In this talk, I will review the work of our team and the broader research community focused on adding various kinds of user control to adaptive information access systems and discuss lessons learned, prospects, and challenges of this direction of research.

March 5, 2023

March 24 Colloquium: "Towards Inclusive and Equitable Human Language Technologies"

I present three of our recent works: 1) Discourse-aware generation models for automatic social media moderation and mediation, 2) Sign language processing, and 3) Equitable and human-like dialogue generation models based on learning theory. Finally, I describe my research vision: Building inclusive and collaborative communicative systems and grounded artificial intelligence models by leveraging the cognitive science of language use alongside formal methods of machine learning.

January 20, 2023

February 24 Colloquium: "The Curious Case of Carbon efficiency in Sustainable Systems"

While current research has mostly focused on reducing the energy footprint, in this talk, we will discuss how improving energy efficiency does not translate to the goal of zero emissions. More importantly, carbon efficiency can be optimized independently of energy efficiency. Toward this end, I will present some examples of mitigating emissions and some directions toward designing carbon-efficient infrastructures. 

January 20, 2023

February 3 Colloquium: "Probabilistic Commonsense Knowledge in Language"

This talk will introduce a probabilistic model representing commonsense knowledge using a learned latent space of geometric embeddings -- probabilistic box embeddings. Using box embeddings makes it possible to handle commonsense queries with intersections, unions, and negations in a way similar to Venn diagram reasoning. Meanwhile, existing evaluations do not reflect the probabilistic nature of commonsense knowledge. To fill in the gap, I will discuss a method of retrieving commonsense related question answer distributions from human annotators and a novel method of generative evaluation. 

January 5, 2023

January 27 Colloquium: "Visualization of the Geometry and Dynamics of Hidden Unit Space"

The juxtaposition of pattern representations is reconfigured at each layer of a multi-layered perceptron. As the activity propagates through the network, the representations are transformed through a systematic progression such that the representation at the penultimate layer is computable at the final stage (e.g., linearly separability for a classification task). 

January 5, 2023

January 20 Colloquium: "Edge-based Real-Time Object Detection for Autonomous Driving"

 In this talk, I will share our recent study on developing a deep-learning-based object detection system on a field-programmable gate arrays (FPGAs) platform for driving applications.

October 25, 2022

October 28 Colloquium: "Great Stories in Computer Science: the case for complexity analysis and empirical testing"

As an instructor of introductory programming courses (007,401 445, 449) at Pitt and similar courses other universities Prof. Hoffman has consistently encountered math hesitancy to the presentation of complexity analysis. In this talk, he will convey an anecdote - a fascinating story in computer science surrounding the binary search algorithm. 

Dr. James Morris
September 9, 2022

September 9 colloquium: Thoughts of a Reformed Computer Scientist: On the Nature of Real and Artificial Intelligence -- James Morris

On September 9th, we are hosting a joint Computer Science Colloquium / Research, Ethics and Society Initiative Seminar, entitled Thoughts of a Reformed Computer Scientist: On the Nature of Real and Artificial Intelligence, given by Dr. James Morris, MBA, PhD (Emeritus Professor of Computer Science, Carnegie Mellon University).

April 8, 2022

April 8 Colloquium: Robust and Delete-Aware LSM-Trees -- Manos Athanassoulis

 Manos Athanassoulis is an Assistant Professor of Computer Science at Boston University, Director and Founder of the BU Data-intensive Systems and Computing Laboratory and co-director of the BU Massive Data Algorithms and Systems Group.

April 1, 2022

April 1 Colloquium: The Case for Reviving Discourse Relations in NLG -- Michael White

Dr. Michael White is a Professor in the Department of Linguistics at The Ohio State University. His research has focused on NLG in dialogue with an emphasis on surface realization, extending also to paraphrasing for ambiguity avoidance and data augmentation in the context of Ohio State's virtual patient dialogue system.

March 25, 2022

March 25 Colloquium: Amazon Supply Chain Optimization Technology: The largest decision-making machine in the world-- Tomas Singliar

Tomas Singliar, University of Pittsburgh CS PhD class of 2008, is a business quantitative scientist with experience in forecasting, inventory, pricing and profitability.

March 18, 2022

March 18 Colloquium: Probabilistic Hashing for Scalable and Sustainable Machine Learning -- Sameh Gobriel

Sameh Gobriel is a senior research scientist at Intel Labs where he leads a team to drive research enabling future Intel products to be best-in-class in performance using software and hardware optimizations.

March 15, 2022

March 15th Colloquium: Bayesian Quadrature -- Henry Chai

Henry Chai is a postdoctoral teaching fellow at Carnegie Mellon University where he teaches an assortment of courses titled "Introduction to Machine Learning" at various levels. He will deliver a faculty recruiting colloquium on Tuesday, March 15th. 

Haipeng Chen
March 14, 2022

March 14th Colloquium: AI for Social Impact: Learning and Optimization in Network and Combinatorial Spaces -- Haipeng Chen

Haipeng Chen is a CRCS postdoctoral fellow at Harvard University.

Sara Riazi
March 8, 2022

March 8th Colloquium: Database Design Theory and Normalization -- Sara Riazi

Sara Riazi is a visiting assistant professor in the Department of Computer Science at the University of North Carolina-Charlotte. She will deliver a faculty recruiting colloquium talk on Tuesday, March 8th.