Events Feed

Start Date: 29 Jan 2019;
Start Time: 02:00PM -
Title: FPSanitizer: Finding instability in floating point applications

Bio:

NULL


Speaker:

Sangeeta Chowdhary


Abstract:
Location: CoRE B (305)
Committee:

Prof. Santosh Nagarakatte (Chair), Prof. Richard Martin, Prof. Mridul Aanjaneya, Prof. Swastik Kopparty

Start Date: 31 Jan 2019;
Start Time: 12:00PM -
Title: Zero-shot Learning from Noisy Text Descriptions

Bio:

NULL


Speaker:

Yizhe Zhu


Abstract:
Location: CBIM 22
Committee:

Prof. Ahmed Elgammal (chair), Prof. Gerard de Melo, Prof. Yongfeng Zhang, Prof. Badri Nath

Start Date: 01 Feb 2019;
Start Time: 04:00PM -
Title: Scalable Data Resilience for In-Memory Data Staging

Bio:

NULL


Speaker:

Shaohua Duan


Abstract:
Location: CoRE A (301)
Committee:

Prof. Manish Parashar (Chair), Prof. Sudarsun Kannan, Prof. Zheng Zhang, Prof. Ahmed Elgammal

Start Date: 05 Feb 2019;
Start Time: 10:30AM -
Title: Security Analytics for Industrial Control System

Bio:

Jiaxing Pi is a research scientist with specialization in big data and security analytics in Siemens Corporation, Corporate Technology. Jiaxing obtained his Ph.D. in Industrial and Systems Engineering from University of Florida. After he joined Siemens, he has been working on the research topic of security analytics for various industrial control system. His past projects include intrusion/anomaly detection systems for water treatment plant, power transmission and distribution system and manufacturing plants. He is currently developing the security situation awareness and root cause analysis system for large distributed control system.


Speaker:

Jiaxing Pi


Abstract:
Location: CoRE A 301
Committee:

James Abello

Start Date: 13 Feb 2019;
Start Time: 10:30AM -
Title: Wagering Mechanisms for Probability Elicitation and Surprising Other Applications

Bio:

David Pennock is a Principal Researcher at Microsoft Research New York City. His largest contributions are novel prediction markets and wagering mechanisms: financial markets harnessed to elicit probabilistic information from a crowd. He has over 70 publications cited 14,000 times and an h-index of 50. He has over twenty patent applications, over twenty press mentions, and has given more than fifty talks including seminars at many of the top CS departments. His Ph.D. is in artificial intelligence and he has been an intellectual and organizational leader in the economics and computation subfield of AI for two decades. He co-founded two research areas, three workshops, and an ACM journal, and was a founding member of three corporate basic-research labs. He served as Assistant Managing Director of MSR NYC for six years. He was Chair of ACM SIGecom, Program co-Chair of ACM EC, and is co-Editor-in-Chief of ACM TEAC. In addition to his primary research area, he has published work in machine learning (including NeurIPS and ICML), theory (including STOC), information retrieval (including a Test of Time Award honorable mention in SIGIR), web science, sponsored search, Bayesian networks, constraint satisfaction, and recommender systems. He led the development of several popular online market games and blogged for Yahoo News. In 2005, he was named to MIT Technology Review’s list of 35 "top technology innovators under age 35" having the potential to profoundly impact the world.


Speaker:

David Pennock


Abstract:
Location: CoRE A 301
Committee:

Fred Roberts (DIMACS)

Start Date: 21 Feb 2019;
Start Time: 10:30AM -
Title: Automated Program Verification via Data-Driven Inference

Bio:

He Zhu is a researcher at Galois, Inc.. He received his Ph.D. from Purdue University advised by Prof. Suresh Jagannathan. He is broadly interested in improving software reliability and security via machine learning, program analysis, and program synthesis with a special focus on type sys-tems, automated reasoning, and formal verification. He authored a PLDI Distinguished Paper in 2018 and received the Maurice H. Halstead Memorial Award in 2016


Speaker:

He Zhu


Abstract:
Location: CoRE A 301
Committee:

Santosh Nagarakatte

Start Date: 21 Feb 2019;
Start Time: 01:00PM -
Title: Approximation with Error Bounds in Spark

Bio:

NULL


Speaker:

Guangyan Hu


Abstract:
Location: CoRE A (301)
Committee:

Prof. Thu Nguyen (Chair), Prof. Ulrich Kremer, Prof. Yongfeng Zhang and Prof. Martin Farach-Colton

Start Date: 22 Feb 2019;
Start Time: 10:30AM -
Title: The multimodality of diagrams - insights from linguistics for computational processing?

Bio:

Tuomo Hiippala (PhD 2014) is Assistant Professor of English Language and Digital Humanities at the University of Helsinki, Finland.

References:
Alikhani & Stone (2018) Arrows are the verbs of diagrams. In Proc. COLING 2018.

Haehn et al. (2019) Evaluating graphical perception with CNNs. IEEE TVCG 25(1).

Hiippala & Orekhova (2018) Enhancing the AI2D Diagrams dataset using Rhetorical Structure Theory. In Proc. LREC 2018.

Kembhavi et al. (2016) A diagram is worth a dozen images. In Proc. ECCV 2016.

Kim et al. (2018) Dynamic graph generation: generating relational knowledge from diagrams. In Proc. CVPR 2018.


Speaker:

Tuomo Hiippala


Abstract:
Location: CoRE A 301
Committee:

Matthew Stone

Start Date: 25 Feb 2019;
Start Time: 10:30AM -
Title: Geometry of Networks: Past Twenty Years and New Challenges

Bio:

Jie Gao is Professor of Computer Science at Stony Brook University. She received BS from the special class for the gifted young program at University of Science and Technology of China in 1999 and Ph.D in computer science from Computer Science department, Stanford University in 2004. She received the NSF Career award in 2006, IMC best paper award in 2009, and multiple awards at Stony Brook CS department on Excellence in Research and Teaching. She has published over 120 referred papers in computer networking and theoretical computer science, and has graduated 14 Ph.D students. She co-chaired the ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), 2018. She is currently serving on the editorial board of ACM Transactions on Sensor Networks and IPSN Steering Committee. She has also served on the editorial board of IEEE Transactions on Automation Science and Engineering and Journal of Discrete Algorithms.


Speaker:

Jie Gao


Abstract:
Location: CoRE A 301
Committee:

Fred Roberts (DIMACS)

Start Date: 28 Feb 2019;
Start Time: 10:30AM -
Title: Defending End Users and Service Providers from Emerging Security Threats

Bio:

Wei Meng is an Assistant Professor in the Department of Computer Science and Engineering at the Chinese University of Hong Kong. He received his Ph.D. degree in Computer Science from the Georgia Institute of Technology in 2017 and his Bachelor’s degree in Computer Science from Tsinghua University in 2012. His research focuses on computer security and privacy. He is particularly interested in designing and building systems to protect end users and applications on the Internet. His research has been published at top conferences such as USENIX Security, WWW, CCS, and NDSS. He currently leads the Computer Security Lab in the CSE department at CUHK.


Speaker:

Wei Meng


Abstract:
Location: CoRE A 301
Committee:

Sudarsun Kannan

Start Date: 04 Mar 2019;
Start Time: 10:30AM -
Title: Allocating Scarce Societal Resources Based on Predictions of Outcomes

Bio:

Sanmay Das is an associate professor in Computer Science and Engineering and the chair of the steering committee of the newly formed Division of Computational and Data Sciences at Washington University in St. Louis. He is vice-chair of the ACM Special Interest Group on Artificial Intelligence and a member of the board of directors of the International Foundation for Autonomous Agents and Multiagent Systems.

Dr. Das has served as program co-chair of the AAMAS and AMMA conferences, and has been recognized with awards for research, service, and teaching, including an NSF CAREER Award and the Department Chair Award for Outstanding Teaching at Washington University.


Speaker:

Sanmay Das


Abstract:
Location: CoRE A 301
Committee:

Fred Roberts (DIMACS)

Start Date: 05 Mar 2019;
Start Time: 10:30AM -
Title: Cop: Broad-Spectrum, Dependable, and Secure Protocol Enforcement Mechanism for Multi-Agent Systems

Bio:

NULL


Speaker:

Chen Cong


Abstract:
Location: CoRE A (301)
Committee:

Prof. Naftaly Minsky (Chair), Prof. Badri Nath, Prof. Wade Trappe, Dr. Victoria Ungureanu (S&P Global)

Start Date: 05 Mar 2019;
Start Time: 03:30PM -
Title: GNM: GridCell Navigational Model

Bio:

NULL


Speaker:

Alireza Naghizadeh


Abstract:
Location: CoRE A 301
Committee:

Prof. Dimitri Metaxas (Chair), Prof. Ahmed Elgammal, Prof. Badri Nath, Prof. Aaron Bernstein

Start Date: 07 Mar 2019;
Start Time: 10:30AM -
Title: Runtime Supports for Scalable and Efficient Big Data Processing

Bio:

Khanh Nguyen is a Ph.D. candidate in the Computer Science Department at UCLA, working with Harry Xu on the intersection of systems and programming languages. He has led the development of a series of compiler and runtime system support to improve the performance of several real-world Big Data systems such as Spark and Hadoop. His work has attracted much attention from both academia and industry. He is a recipient of the Google Ph.D. Fellowship in Systems and Networking, and a Facebook Ph.D. Fellowship Finalist.


Speaker:

Khanh Nguyen


Abstract:
Location: CoRE A 301
Committee:

Richard Martin

Start Date: 11 Mar 2019;
Start Time: 10:30AM -
Title: Towards Efficient and Reliable Data Center Systems

Bio:

Danyang Zhuo is a sixth-year Ph.D. student in Computer Science and Engineering at the University of Washington, where he is advised by Tom Anderson and Arvind Krishnamurthy. His work spans computer systems and networking, and his recent work focuses on improving the reliability and efficiency of cloud operating systems and data center network architectures. Before starting at the University of Washington, he received his bachelor degree in Electrical Engineering at the University of Illinois Urbana Champaign.


Speaker:

Danyang Zhuo


Abstract:
Location: CoRE A 301
Committee:

Srinivas Narayana

Start Date: 12 Mar 2019;
Start Time: 10:30AM -
Title: Kernel distances for distinguishing and sampling from probability distributions

Bio:

Dougal Sutherland is a postdoctoral researcher at the Gatsby Computational Neuroscience Unit, University College London, working with Arthur Gretton. He received his PhD in 2016 from Carnegie Mellon University, advised by Jeff Schneider. His research focuses on problems of learning about distributions from samples, including training implicit generative models, density estimation, two-sample testing, and distribution regression. His work combines kernel frameworks with deep learning, and aims for theoretical grounding of practical results.


Speaker:

Dougal Sutherland


Abstract:
Location: CoRE A 301
Committee:

Dimitris Metaxas

Start Date: 14 Mar 2019;
Start Time: 10:30AM -
Title: Bayesian Deep Learning: A Probabilistic Framework to Unify Deep Learning and Graphical Models

Bio:

Dr. Hao Wang is currently a Postdoctoral Associate at the Computer Science & Artificial Intelligence Lab (CSAIL) of MIT, working with Dina Katabi and Tommi Jaakkola. He received his PhD degree from the Hong Kong University of Science and Technology, as the sole recipient of the School of Engineering PhD Research Excellence Award in 2017. He has been a visiting researcher in the Machine Learning Department of Carnegie Mellon University. His research focuses on statistical machine learning, deep learning, and data mining, with broad applications on recommender systems, healthcare, user profiling, social network analysis, text mining, etc. His work on Bayesian deep learning for recommender systems and personalized modeling has inspired hundreds of follow-up works published at top conferences such as AAAI, ICML, IJCAI, KDD, NIPS, SIGIR, and WWW. It has received over 500 citations, becoming the most cited paper at KDD 2015. In 2015, he was awarded the Microsoft Fellowship in Asia and the Baidu Research Fellowship for his innovation on Bayesian deep learning and its applications on data mining and social network analysis.


Speaker:

Hao Wang


Abstract:
Location: CoRE A 301
Committee:

Dimitris Metaxas

Start Date: 14 Mar 2019;
Start Time: 03:00PM -
Title: Generating Explanation Sentences for Personalized Recommendation

Bio:

NULL


Speaker:

Hanxiong Chen


Abstract:
Location: CoRE 305 (B)
Committee:

Prof. Yongfeng Zhang (Chair), Prof. Matthew Stone, Prof. Gerard de Melo, Prof. Desheng Zhang

Start Date: 25 Mar 2019;
Start Time: 10:30AM -
Title: Maximal Mutual Information Predictive Coding for Natural Language Processing

Bio:

Karl Stratos is a research assistant professor at Toyota Technological Institute at Chicago (TTIC). His research centers on statistical approaches to unsupervised learning in natural language processing. He obtained his PhD from Columbia University where he worked with Michael Collins and Daniel Hsu and spent summers at Microsoft Research New England and Google New York. He was a senior research scientist at Bloomberg L.P. and an adjunct assistant professor at Columbia University before coming to TTIC in 2017.


Speaker:

Karl Stratos


Abstract:
Location: CoRE A 301
Committee:

Sungjin Ahn

Start Date: 26 Mar 2019;
Start Time: 10:30AM -
Title: Transparent Computing Systems Enabled by Program Analysis

Bio:

Shiqing Ma is a Ph.D. candidate in the Department of Computer Science at Purdue University, co-advised by Professors Xiangyu Zhang and Dongyan Xu. His research interests lie in solving security and software engineering problems via program analysis techniques with a focus on improving the transparency of modern computing systems. He is the recipient of two Distinguished Paper Awards at ISOC NDSS 2016 and USENIX Security 2017.


Speaker:

Shiqing Ma


Abstract:
Location: CoRE A 301
Committee:

Desheng Zhang

Start Date: 26 Mar 2019;
Start Time: 01:30PM -
Title: AutoNet: Automated Network Construction from Massive Text Corpora

Bio:

Jingbo Shang is a Ph.D. candidate in Department of Computer Science, University of Illinois at Urbana-Champaign. He received his B.E. from Computer Science Department, Shanghai Jiao Tong University, China. His research focuses on mining and constructing structured knowledge from massive text corpora with minimum human effort. His research has been recognized by many prestigious awards, including Computer Science Excellence Scholarship from CS@Illinois, Grand Prize of Yelp Dataset Challenge in 2015, Google PhD Fellowship in Structured Data and Database Management in 2017, and C.W. Gear Outstanding Graduate Award in 2018. Moreover, his technologies have been transferred and applied in a wide spectrum of industries (e.g., high-tech, biomedical, financial) and open-source tools on Github have received thousands of stars and hundreds of forks.


Speaker:

Jingbo Shang


Abstract:
Location: CoRE A 301
Committee:

Yongfeng Zhang

Start Date: 28 Mar 2019;
Start Time: 10:30AM -
Title: Rethinking the Hardware-Software contract: Enabling practical and general cross-layer optimizations

Bio:

Nandita Vijaykumar is a Ph.D. candidate at Carnegie Mellon University, advised by Prof. Onur Mutlu and Prof. Phillip Gibbons. She is also currently a visiting student at ETH Zurich. Her research focuses on the interaction between programming models, system software, and hardware architecture in an increasingly diverse compute landscape, with a focus on memory systems and modern accelerators like GPUs. She is excited about enabling cross-layer full-stack solutions to make future systems highly efficient and easy-to-program. She is the recipient of the Benjamin Garver Lamme/Westinghouse Fellowship at CMU. During her Ph.D., she has been fortunate to intern at Microsoft Research, Nvidia Research, and Intel Labs.


Speaker:

Nandita Vijaykumar


Abstract:
Location: CoRE A 301
Committee:

Badri Nath

Start Date: 01 Apr 2019;
Start Time: 10:30AM -
Title: Conversational Machine Learning

Bio:

Shashank Srivastava recently received his PhD from the Machine Learning department at CMU in 2018, and currently works at Microsoft Research. Shashank's research interests lie in conversational learning, interactive AI and grounded language understanding, and his dissertation focuses on helping machines learn from human interactions. Shashank has an undergraduate degree in Computer Science from IIT Kanpur, and a Master’s degree in Language Technologies from CMU. He received the Yahoo InMind Fellowship for 2016-17. His research has been covered by popular media outlets including GeekWire and New Scientist.


Speaker:

Shashank Srivastava


Abstract:
Location: CoRE A 301
Committee:

Abdeslam Boularias

Start Date: 04 Apr 2019;
Start Time: 01:00PM -
Title: Toward a Fairer Information Retrieval System

Bio:
Speaker:

Ruoyuan Gao


Abstract:
Location: Hill 482
Committee:

Prof. Chirag Shah (Chair), Prof. William Steiger, Prof. Yongfeng Zhang, Prof. Martin Farach-Colton

Start Date: 05 Apr 2019;
Start Time: 01:30PM -
Title: Machine Learning driven Large-Scale Medical Image Analysis and Its Applications in Cardiac Magnetic Resonance Imaging

Bio:
Speaker:

Dong Yang


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris Metaxas (Chair), Prof. Konstantinos Michmizos, Prof. Yongfeng Zhang, and Prof. James Duncan (Yale University)

Start Date: 11 Apr 2019;
Start Time: 01:00PM -
Title: Inferring 3D Shapes of Unknown Rigid Objects in Clutter through Inverse Physics Reasoning

Bio:
Speaker:

Changkyu Song


Abstract:
Location: 1 Spring Street, Room 403, New Brunswick
Committee:

Prof. Abdeslam Boularias (Chair), Prof. Kostas Bekris, Prof. Jingjin Yu, Prof. Richard Martin.

Start Date: 12 Apr 2019;
Start Time: 10:00AM -
Title: Scheduling edge and in-transit computing resources for stream processing applications

Bio:
Speaker:

Ali Reza Zamani


Abstract:
Location: CoRE A (301)
Committee:

Prof. Manish Parashar (Chair), Prof. Ulrich Kremer, Prof. Srinivas Narayana, Adrian Lebre, Inria

Start Date: 16 Apr 2019;
Start Time: 01:00PM -
Title: Neural Graph Reasoning for Explainable Decision Making

Bio:
Speaker:

Yikun Xian


Abstract:
Location: CoRE A (301)
Committee:

Prof. Shan Muthukrishnan (Chair), Prof. Yongfeng Zhang, Prof. Pranjal Awasthi, Prof. Amélie Marian

Start Date: 18 Apr 2019;
Start Time: 10:30AM -
Title: Weakly Supervised Nuclei Segmentation in Histopathology Images

Bio:
Speaker:

Hui Qu


Abstract:
Location: CBIM 22
Committee:

Profl. Dimitri Metaxas (Chair), Prof. Konstantinos Michmizos, Prof. Georgios Moustakides, Prof. Badri Nath

Start Date: 22 Apr 2019;
Start Time: 10:30AM -
Title: Enabling Transparent Vehicular Mobility Modeling at Individual Levels with Full Penetration

Bio:
Speaker:

Yu Yang


Abstract:
Location: CoRE 305 (B)
Committee:

Prof. Desheng Zhang (Chair), Prof. Richard Martin, Prof. Yongfeng Zhang, Prof. Mubbasir Kapadia

Start Date: 22 Apr 2019;
Start Time: 03:30PM -
Title: Grounded and Interpretable Learning-Based Models for Visual Recognition Tasks

Bio:
Speaker:

Zachary Daniels


Abstract:
Location: CBIM 22
Committee:

Prof. Metaxas (Chair), Prof. Michmizos, Prof. Moustakides, Prof. Gerasoulis

Start Date: 23 Apr 2019;
Start Time: 10:00AM -
Title: Deep learning approaches in medical image analysis focusing on MRI reconstruction

Bio:
Speaker:

Qiaoying Huang


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris Metaxas (Chair), Prof. Georgios Moustakides, Prof. Desheng Zhang, Prof. Shubhangi Saraf

Start Date: 23 Apr 2019;
Start Time: 10:30AM -
Title: Cooperation in Humans and Machines

Bio:

Dr. Patrick Shafto is the Henry Rutgers Term Chair in Data Science and Associate Professor of Mathematics and Computer Science at Rutgers University - Newark. Research in his lab focuses on theoretical and empirical foundations of cooperation and learning in humans and machines. He has received numerous honors and awards including an NSF CAREER award and his research has formed the basis for successful data science start-up companies eventually acquired by Salesforce and Tableau. His research is supported by multiple NSF directorates (EHR, CISE, SBE), DARPA, DoD, the intelligence community, and the NIH.


Speaker:

Patrick Shafto


Abstract:
Location: CoRE A 301
Committee:

Matthew Stone

Start Date: 24 Apr 2019;
Start Time: 01:30PM -
Title: Instance Segmentation of Neural Cells

Bio:
Speaker:

Jingru Yi


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris Metaxas (Chair), Prof. Georgios Moustakides, Prof. Sungjin Ahn Srinivas, Prof. Narayana Ganapathy

Start Date: 25 Apr 2019;
Start Time: 11:00AM -
Title: Tables evidence grounding

Bio:
Speaker:

Mohamed Abdellatif


Abstract:
Location: CoRE B (305)
Committee:

Prof. Ahmed Elgammal, Prof. Bahman Kalantari, Prof. Abdeslam Boularias, Prof. Gerard De Melo

Start Date: 25 Apr 2019;
Start Time: 02:00PM -
Title: Collaborative Urban-Scale Vehicle Sensing Based on Heterogeneous Fleets

Bio:
Speaker:

Xiaoyang Xie


Abstract:
Location: CoRE A (301)
Committee:

Prof. Desheng Zhang (Chair), Prof. Zheng Zhang, Prof. Yongfeng Zhang and Prof. Kostas Bekris

Start Date: 25 Apr 2019;
Start Time: 04:00PM -
Title: Understanding Long-Term Evolving Patterns of Shared Electric Vehicle Networks

Bio:
Speaker:

Guang Wang


Abstract:
Location: CoRE A (301)
Committee:

Prof. Desheng Zhang (Chair), Prof. Zheng Zhang, Prof. Yongfeng Zhang, Prof. Abdeslam Boularias

Start Date: 29 Apr 2019;
Start Time: 01:30PM -
Title: Optimal Topological Cycles and Their Application in Cardiac Trabeculae Restoration

Bio:
Speaker:

Pengxiang Wu


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris Metaxas (Chair), Prof. George Moustakides, Prof. Desheng Zhang, Prof. Sudarsun Kannan

Start Date: 29 Apr 2019;
Start Time: 03:30PM -
Title: Towards improved inference and generation for bidirectional generative adversarial models

Bio:
Speaker:

Yu Tian


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris Metaxas (Chair), Prof. Casimir Kulikowski, Prof. Yongfeng Zhang, Prof. Georgios Moustakides

Start Date: 30 Apr 2019;
Start Time: 10:00AM -
Title: EXIMIUS: A Measurement Framework for Explicit and Implicit Urban Traffic Sensing

Bio:
Speaker:

Zhou Qin


Abstract:
Location: CoRE B (305)
Committee:

Prof. Desheng Zhang (Chair), Prof. Richard Martin, Prof. Yongfeng Zhang, Prof. Konstantinos Michmizos.

Start Date: 30 Apr 2019;
Start Time: 01:00PM -
Title: Triangle Algorithm: A Fast Oracle for Convex Hull Membership Queries in Machine Learning and Computational Geometry Applications

Bio:
Speaker:

Yikai Zhang


Abstract:
Location: CoRE B (305)
Committee:

Prof. Bahman Kalantari (Chair), Prof. Pranjal Awasthi, Prof. William Steiger, Prof. Mridul Aanjaneya

Start Date: 02 May 2019;
Start Time: 02:00PM -
Title: Brain-morphic algorithms on Neuromorphic Hardware: Towards energy-efficient and versatile Neu-Robotics

Bio:
Speaker:

Guangzhi Tang


Abstract:
Location: CoRE A 301
Committee:

Prof. Konstantinos Michmizos (Chair), Prof. Kostas Bekris, Prof. Santosh Nagarakatte, Prof. Badri Nath

Start Date: 07 May 2019;
Start Time: 11:00AM -
Title: The Interesting Parts of Vision Happen Outside the Feedforward Pathway

Bio:

John Tsotsos is Distinguished Research Professor of Vision Science at York University. He received his doctorate in Computer Science from the University of Toronto. In 1980 he founded the Computer Vision Group at the University of Toronto, which he led for 20 years. In 2000, he moved to York University to become the Director of the Centre for Vision Research. He became the founding Director of York's Centre for Innovation in Computing in 2014. He has been a CIFAR Fellow, is an IEEE Fellow and Canada Research Chair in Computational Vision. Other honours include a 1987 inaugural Marr Prize citation, the 2006 Canadian Image Processing and Pattern Recognition Society Award for Research Excellence and Service, the 1st President’s Research Excellence Award by York University on the occasion of the University’s 50th anniversary in 2009, and the 2011 Geoffrey J. Burton Memorial Lectureship from the United Kingdom's Applied Vision Association for significant contribution to vision science. Elected as Fellow of the Royal Society of Canada in 2010, he became the first computer scientist to receive its 2015 Sir John William Dawson Medal for sustained excellence in multiple domains.


Speaker:

John Tsotsos


Abstract:
Location: CoRE Auditorium
Committee:

Dimitris Metaxas

Start Date: 07 May 2019;
Start Time: 03:00PM -
Title: Brain-informed learning models of movement primitives for neurorehabilitation robots

Bio:
Speaker:

Neelesh Kumar


Abstract:
Location: CBIM 22
Committee:

Prof. Konstantinos Michmizos (Chair), Prof. Tomasz Imielinski, Prof. Ahmed Elgammal, Prof. Srinivas Narayana

Start Date: 09 May 2019;
Start Time: 10:00AM -
Title: Performance Profilers and Debugging Tools for OpenMP programs

Bio:
Speaker:

Nader Boushehrinejad


Abstract:
Location: CoRE 305
Committee:

Prof Santosh Nagarakatte (Chair), Prof Badri Nath, Prof Srinivas Narayana, Prof Martha Kim (Columbia University)

Start Date: 09 May 2019;
Start Time: 10:30AM -
Title: A new approach for prediction of pedestrian trajectories based only on images.

Bio:
Speaker:

Blerta Lindqvist


Abstract:
Location: CoRE A 301
Committee:

Prof. Kristin Dana, Prof. Casimir Kulikowski, Prof. Kostas Bekris and Prof. Desheng Zhang

Start Date: 09 May 2019;
Start Time: 12:30PM -
Title: Towards Less Artificial Intelligence: Recurrent Spiking Neuronal-Astrocytic Networks Operating at the Edge of Chaos

Bio:
Speaker:

Vladimir Ivanov


Abstract:
Location: CBIM 22
Committee:

Professor Konstantinos Michmizos (Chair), Professor Casimir Kulikowski, Professor Thu Nguyen, Professor Eric Allender

Start Date: 09 May 2019;
Start Time: 01:00PM -
Title: Performance and Correctness Debugging Techniques for Task Parallel Programs

Bio:
Speaker:

Adarsh Yoga


Abstract:
Location: CoRE B 305
Committee:

Prof. Santosh Nagarakatte (Chair), Prof. Ulrich Kremer, Prof. Sudarsun Kannan, and Dr. Madanlal Musuvathi (Microsoft Research)

Start Date: 09 May 2019;
Start Time: 02:30PM -
Title: Automated analysis of hatching lines in drawings for attribution and authentication using convolutional neural networks

Bio:
Speaker:

Shahrzad Ziaee


Abstract:
Location: CoRE A (301)
Committee:

Prof. Ahmed Elgammal (Chair), Prof. Alex Borgida, Prof. Casimir Kulikowski, Prof. Uli Kremer

Start Date: 10 May 2019;
Start Time: 10:00AM -
Title: Scheduling edge and in-transit computing resources for stream processing applications

Bio:
Speaker:

Ali Reza Zamani Zadeh Najari


Abstract:
Location: CoRE A 301
Committee:

Prof. Manish Parashar (Chair), Prof. Ulrich Kremer, Prof. Srinivas Narayana, Prof. Adrien Lebre (IMT Atlantique)

Start Date: 14 May 2019;
Start Time: 12:00PM -
Title: Multi-Agent Narrative Generation With Commonsense Knowledge-Based Environment Modeling

Bio:
Speaker:

Xun Zhang


Abstract:
Location: CBIM 22
Committee:

Prof. Mubbasir Kapadia (Chair), Prof. Mridul Aanjaneya, Prof. Jingjin Yu, Prof. Sudarsun Kannan

Start Date: 16 May 2019;
Start Time: 02:00PM -
Title: Computational Astrocyence: Astrocytic Learning in Spiking Neural Networks

Bio:
Speaker:

Ioannis Polykretis


Abstract:
Location: CBIM 22
Committee:

Prof. Konstantinos Michmizos, Prof. Casimir Kulikowski, Prof. Dimitri Metaxas, Prof. Bahman Kalantari

Start Date: 28 May 2019;
Start Time: 03:00PM -
Title: Representation Learning for Predicting Information Spread in Dynamic Heterogeneous Networks

Bio:
Speaker:

Vahid Azizi


Abstract:
Location: CoRE B (305)
Committee:

Prof. Mubbasir Kapadia (Chair), Prof. Gerald De Melo, Prof. Mridul Aanjaneya, Prof. Aaron Bernstein

Start Date: 03 Jun 2019;
Start Time: 11:00AM -
Title: Effective Medical Image Segmentation for Osteoarthritis Analysis.

Bio:
Speaker:

Chaowei Tan


Abstract:
Location: CBIM 22
Committee:

Dimitris Metaxas (Chair), Prof. Kang Li, Prof. Jingjin Yu, Dr. Xin Dou (SenseBrain Technology Limited, Princeton)

Start Date: 13 Jun 2019;
Start Time: 09:30AM -
Title: Trajectory Interpolation and Scenario Generalization in Crowd Simulation

Bio:
Speaker:

Gang Qiao


Abstract:
Location: CoRE A (301)
Committee:

Prof. Vladimir Pavlovic (Chair), Prof. Santosh Nagarakatte, Prof. Yongfeng Zhang, Prof. Mubbasir Kapadia

Start Date: 13 Jun 2019;
Start Time: 11:00AM -
Title: Joint Representation Learning of Images and Unstructured Text with Application to Dynamic Multimodal Social Networks

Bio:
Speaker:

Hareesh Ravi


Abstract:
Location: CoRE A (301)
Committee:

Prof. Mubbasir Kapadia (Chair), Prof. Gerard De Melo, Prof. Dimitris Metaxas, Prof. Amelie Marian

Start Date: 13 Jun 2019;
Start Time: 02:00PM -
Title: Meal Image Generation from Recipe

Bio:
Speaker:

Fangda Han


Abstract:
Location: CoRE A (301)
Committee:

Prof. Vladimir Palvovic (Chair), Prof. Dimitri Metaxas, Prof. Ahmed Elgammal, Prof. Ulrich Kremer

Start Date: 14 Jun 2019;
Start Time: 09:30AM -
Title: Learning Latent Representation: A Key to Domain Adaptation and Disentangling

Bio:
Speaker:

Pritish Sahu


Abstract:
Location: CoRE A (301)
Committee:

Prof. Vladimir Pavlovic (Chair), Prof. Dimitri Metaxas, Prof. Yongfeng Zhang, Prof. Swastik Kopparty

Start Date: 21 Aug 2019;
Start Time: 10:30AM -
Title: Scalable and Congestion-aware Routing for Autonomous Mobility-On-Demand via Frank-Wolfe Optimization

Bio:

Kiril Solovey is a Postdoctoral Scholar supported by the Fulbright Scholars Program at the Autonomous Systems Lab, Department of Aeronautics & Astronautics, Stanford University, hosted by Prof. Marco Pavone. His research focuses on algorithmic aspects of robotics. He is particularly interested in the design and analysis of techniques for robot motion planning, multi-robot systems, and autonomous mobility on demand (AMoD). Prior to Stanford, Kiril was a Ph.D. student at Tel Aviv University working with Prof. Dan Halperin in the Computational Geometry Lab supported by the Clore Israel Foundation.


Speaker:

Kiril Solovey


Abstract:
Location: 1 Spring street, New Brunswick, Room 204
Committee:

Kostas Bekris

Start Date: 27 Aug 2019;
Start Time: 10:00AM -
Title: Taming Combinatorial Challenges in Clutter Removal

Bio:
Speaker:

Wei Tang


Abstract:
Location: 1 Spring St., New Brunswick, NJ 08901/Room 403
Committee:

Prof. Jingjin Yu (Chair), Prof. Kostas Bekris, Prof. Abdeslam Boularias, Prof. William Steiger

Start Date: 27 Aug 2019;
Start Time: 03:00PM -
Title: Providing Concurrency in Direct Access File Systems

Bio:
Speaker:

Yujie Ren


Abstract:
Location: CoRE B 305
Committee:

Prof. Sudarsun Kannan (Chair), Prof. Santosh Nagarakatte, Prof. Thu Nguyen, Prof. Ulrich Kremer and Prof. Jingjin Yu

Start Date: 04 Sep 2019;
Start Time: 11:00AM -
Title: New Results on Projections

Bio:
Speaker:

Guy Moshkovitz


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing

Start Date: 06 Sep 2019;
Start Time: 01:00PM -
Title: Searching Heterogeneous Personal Data

Bio:
Speaker:

Daniela Vianna


Abstract:
Location: CoRE A (301)
Committee:

Prof. Amelie Marian (Chair), Prof. Thu Nguyen, Prof. Yongfeng Zhang, and Dr. Divesh Srivastava

Start Date: 16 Sep 2019;
Start Time: 01:00PM -
Title: Parallelism-Driven Performance Analysis Techniques for Task Parallel Programs

Bio:
Speaker:

Adarsh Yoga


Abstract:
Location: CoRE A (301)
Committee:

Prof. Santosh Nagarakatte (Chair), Prof. Ulrich Kremer, Prof. Sudarsun Kannan, and Dr. Madanlal Musuvathi (Microsoft Research)

Start Date: 19 Sep 2019;
Start Time: 10:00AM -
Title: Computational Analysis of Fine Art Paintings

Bio:
Speaker:

Diana Kim


Abstract:
Location: CoRE B (305)
Committee:

Prof. Ahmed Elgammal (Chair), Prof. Michmizos, Prof. Gerard De Melo, Prof. Zhang.

Start Date: 24 Sep 2019;
Start Time: 10:30AM -
Title: Semantic Graph Convolutional Networks for 3D Human Pose Regression

Bio:
Speaker:

Long Zhao


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris N. Metaxas (Chair); Prof. Mubbasir Kapadia; Prof. Yongfeng; Zhang Prof. Dong Deng

Start Date: 25 Sep 2019;
Start Time: 10:00AM -
Title: A Model for Concurrent Priority Queue on Manycore Architectures

Bio:
Speaker:

Chaozhang Huang


Abstract:
Location: Core 305
Committee:

Professor Zheng Zhang (chair) Professor Desheng Zhang Professor Yongfeng Zhang

Start Date: 25 Sep 2019;
Start Time: 11:00AM -
Title: How to Store a Random Walk

Bio:

Huacheng Yu is an associate research scholar in the department of computer science at Princeton University. Prior to Princeton, he was a postdoc in the Theory of Computation group at Harvard University, after receiving his PhD from Stanford University in 2017.


Speaker:

Huacheng Yu


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 30 Sep 2019;
Start Time: 11:00AM -
Title: An Effective Graph Edge Partition Model for GPU Computing

Bio:
Speaker:

Yanhao Chen


Abstract:
Location: CoRE B (305)
Committee:

Prof. Zheng Zhang (Chair), Prof. Desheng Zhang, Prof. Ulrich Kremer , Prof. Martin Farach-Colton

Start Date: 30 Sep 2019;
Start Time: 01:30PM -
Title: Effective Medical Image Segmentation for Osteoarthritis Analysis

Bio:
Speaker:

Chaowei Tan


Abstract:
Location: CBIM 22
Committee:

Prof. Dimitris N. Metaxas (Chair),Prof. Kang Li, Prof. Jingjin Yu, Dr. Xin Dou (SenseBrain Technology Limited, Princeton)

Start Date: 02 Oct 2019;
Start Time: 09:45AM -
Title: Implicit Regularization for Optimal Sparse Recovery

Bio:
Speaker:

Varun Kanade


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DiMACS Theory of Computing Seminar

Start Date: 02 Oct 2019;
Start Time: 09:45AM -
Title: Small-loss bounds for online learning with partial information

Bio:

Thodoris Lykouris is a Postdoctoral Researcher in the Machine Learning group of Microsoft Research NYC. He recently graduated with a Ph.D. in Computer Science from Cornell University where he was advised by Eva Tardos. His research spans across the areas of machine learning, algorithms, optimization, and economics, with a particular emphasis on enhancing online decision-making in complex multi-agent systems. Thodoris is a recipient of the 2018 Google Ph.D. Fellowship on "Algorithms, Optimization, and Markets" and a finalist in the 2018 INFORMS Nicholson and 2017 Applied Probability Society Student Paper Competitions. He was a research intern at Microsoft Research Redmond (summer 2018), Google Research NYC (summer 2017), and Microsoft Research India (summer 2015). He was also a visiting student at TTI-Chicago (March-May 2018) and the Simons Institute at Berkeley (fall 2015, spring 2018). Thodoris received his Diploma from the EECS department of the National Technical University of Athens.


Speaker:

Thodoris Lykouris


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 09 Oct 2019;
Start Time: 11:00AM -
Title: Convex Set Disjointness, Distributed Learning of Halfspace

Bio:
Speaker:

Shay Moran


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 16 Oct 2019;
Start Time: 11:00AM -
Title: Nullstellensatz Size-Degree Trade-offs from Reversible Pebbling

Bio:
Speaker:

Rob Robere


Abstract:
Location: CoRE 431
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 23 Oct 2019;
Start Time: 11:00AM -
Title: The asymptotic spectrum of tensors and barriers for fast matrix multiplication

Bio:
Speaker:

Jeroen Zuiddam


Abstract:
Location: CoRE 431
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 30 Oct 2019;
Start Time: 11:00AM -
Title: An Improved Lower Bound for Sparse Reconstruction from Subsampled Hadamard Matrices

Bio:
Speaker:

Jarosław Błasiok


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 06 Nov 2019;
Start Time: 09:45AM -
Title: On Rich 2-to-1 Games

Bio:
Speaker:

Dor Minzer


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 06 Nov 2019;
Start Time: 11:00AM -
Title: Recent Advances in Stochastic Gradient Methods: From Convex to Non-convex Optimization and Deep Learning

Bio:

Mert Gürbüzbalaban is an assistant professor at Rutgers University. Previously, he was a postdoctoral associate at the Laboratory for Information and Decision Systems (LIDS) at MIT. He is broadly interested in optimization and computational science driven by applications in large-scale information and decision systems. He received his B.Sc. degrees in Electrical Engineering and Mathematics as a valedictorian from Boğaziçi University, Istanbul, Turkey, the “Diplôme d’ingénieur” degree from École Polytechnique, France, and the M.S. and Ph.D. degrees in (Applied) Mathematics from the Courant Institute of Mathematical Sciences, New York University.

Dr. Gürbüzbalaban received the Kurt Friedrichs Prize (given by the Courant Institute of New York University for an outstanding thesis) in 2013, Bronze Medal in the École Polytechnique Scientific Project Competition in 2006, the Nadir Orhan Bengisu Award (given by the electrical-electronics engineering department of Boğaziçi University to the best graduating undergraduate student) in 2005 and the Bülent Kerim Altay Award from the Electrical-Electronics Engineering Department of Middle East Technical University in 2001. He received funding from a variety of sources including multiple programs at the U.S. National Science Foundation. He is also a co-recipient of the Best Paper Runner-Up Award from the International Conference on Machine Learning, 2019.


Speaker:

Mert Gurbuzbalaban


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 13 Nov 2019;
Start Time: 11:00AM -
Title: Optimal Data Acquisition for Statistical Estimation

Bio:
Speaker:

Juba Zian


Abstract:
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 20 Nov 2019;
Start Time: 11:00AM -
Title: Online Vector Balancing and Geometric Discrepancy

Bio:
Speaker:

Sahil Singla


Abstract:
Location: CoRE 431
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 22 Nov 2019;
Start Time: 11:00AM -
Title: ACTION GRAMMARS: THE KEY TO AI AND ROBOTICS

Bio:

Yiannis Aloimonos is Professor of Computational Vision and Intelligence at the Department of Computer Science, University of Maryland, College Park, and the Director of the Computer Vision Laboratory at the Institute for Advanced Computer Studies (UMIACS). He is also affiliated with the Institute for Systems Research and the Neural and Cognitive Science Program. He was born in Sparta, Greece and studied Mathematics in Athens and Computer Science at the University of Rochester, NY (PhD 1990). He is interested in Active Perception and the modeling of vision as an active, dynamic process for real time robotic systems. For the past five years he has been working on bridging signals and symbols, specifically on the relationship of vision to reasoning, action and language.


Speaker:

Yiannis Aloimonos


Abstract:
Location: CoRE A 301
Committee:

Dimitris Metaxas

Start Date: 25 Nov 2019;
Start Time: 08:00AM -
Title: Learning Biomarkers from Biomedical Image Data

Bio:

Dr. Sharon Xiaolei Huang is currently an associate professor in the College of Information Sciences and Technology at the Pennsylvania State University, University Park, PA, USA. She is also an affiliated faculty member of Penn State’s Huck Institutes of the Life Sciences. Her research interests lie at the intersection of biomedical image analysis, machine learning, and computer vision. She has over 130 publications (including journal articles, book chapters, and refereed conference papers) and holds 7 patents. She is an associate editor for the Computer Vision and Image Understanding journal. She received her Bachelor’s degree in computer science from Tsinghua University, and her Master’s and doctoral degrees in computer science from Rutgers University. Her research has been funded by the NIH, NSF, the Howard Hughes Medical Institute, and the Pennsylvania state.

References:
https://faculty.ist.psu.edu/suh972

https://scholar.google.com/citations?user=iTtzc1UAAAAJ&hl=en


Speaker:

Dr. Sharon Xiaolei Huang


Abstract:
Location: CoRE A 301
Committee:

Dimitris Metaxas

Start Date: 02 Dec 2019;
Start Time: 04:00PM -
Title: Fast and Optimal Methods for Object Rearrangement and Multi-Robot Path Planning

Bio:
Speaker:

Shuai Han


Abstract:
Location: 1 Spring Street (CAC), Room 403
Committee:

Prof. Jingjin Yu (Chair), Prof. Kostas Bekris, Prof. Abdeslam Boularias, Prof. Sepehr Assadi

Start Date: 03 Dec 2019;
Start Time: 10:30AM -
Title: Learning Natural Language Semantics with Heterogeneous Supervision

Bio:

Gerard de Melo is an Assistant Professor in the Department of Computer Science at Rutgers University, where he heads the Deep Data Lab. Over the years, he has published around 150 papers on natural language processing, data science, and AI, being awarded Best Paper awards at CIKM 2010, ICGL 2008, and the NAACL 2015 Workshop on Vector Space Modeling, in addition to the WWW 2011 Best Demonstration Award, an ACL
2014 Best Paper Honorable Mention, a nomination for Best Student Paper at ESWC 2015, and a nomination for Best Paper at the IEEE Conference on Semantic Computing 2018. Prior to joining Rutgers, he was a faculty member at Tsinghua University and a Post-Doctoral Research Scholar at ICSI/UC Berkeley. He received his doctoral degree at the Max Planck Institute for Informatics.


Speaker:

Gerard de Melo


Abstract:
Location: CoRE A 301
Committee:

Matthew Stone

Start Date: 10 Dec 2019;
Start Time: 10:30AM -
Title: Scaling Up Computational Physics for Real World Applications

Bio:

Dr. Mridul Aanjaneya is an Assistant Professor in the Department of Computer Science at Rutgers University. Prior to joining Rutgers, he was a postdoctoral researcher in the Department of Computer Sciences at the University of Wisconsin - Madison. He obtained his Ph.D. in Computer Science from Stanford University. While at Stanford, he also worked as a consultant in the Spatial Technologies team at the Nokia Research Center for two years. Mridul's research lies at the intersection of Computer Graphics, Scientific and High-Performance Computing, and Computational Physics. More specifically, he is interested in the design of models, computational techniques, and robust numerical algorithms that can facilitate high-level tasks such as the use of simulations in biomechanics, computational imaging, or robotics. He is a recipient of the Ralph E. Powe Junior Faculty Enhancement Award 2019, sponsored by the Oak Ridge Associated Universities (ORAU).


Speaker: Mridul Aanjaneya
Abstract:
Location: CoRE A 301
Committee:

Matthew Stone

Start Date: 11 Dec 2019;
Start Time: 11:00AM -
Title: Seminar: Double-samplers and local-to-global list decoding

Bio:
Speaker:

Irit Dinur


Abstract: I will describe a recent work that uses so-called “double-samplers” for list decoding. Double samplers are multi-layered graphs that are derived from high dimensional expanders, and whose existence is quite non-trivial. The talk will be flexible depending on the audience preference I can expand on the coding application or on the double samplers themselves. Based on a joint work with Harsha, Livni, Kaufman and Ta-Shma
Location: CoRE A 301
Committee:

Rutgers/DIMACS Theory of Computing Seminar

Start Date: 08 Jan 2020;
Start Time: 02:00PM -
Title: TRADING QUALITY FOR RESOURCE CONSUMPTION THROUGH APPROXIMATION MANAGEMENT

Bio:
Speaker:

Liu Liu


Abstract: The goal of traditional optimizations is to map applications onto limited machine resources such that application performance is maximized while application semantics (program correctness) is preserved. Semantics is thought of as a unique mapping from inputs to outcomes. Relaxing application semantics through approximations has the potential of orders of magnitude performance improvements by trading off outcome quality for resource usage. Here, an execution outcome is not only based on its inputs but also resource availability and user quality expectations. Emerging approximation techniques provides various ways to trade-off output quality for lower resource consumption. However, as a developer, the guidance and support on how to utilize the power of approximation in everyday applications are limited and rarely discussed in recent works. The offline training overhead to support approximation is usually huge, but often be treated as "free." Besides, it is surprising that end-users involvement is always overlooked when determining the quality notion, which should be highly subjective. Finally, supporting approximation in a multi-programming environment is crucial to let approximation be widely accepted as a general technique. In this dissertation, I introduce RAPIDS, Reconfiguration, Approximation, Preferences, Implementation, Dependencies, and Structure, a framework for developing and executing applications suitable for dynamic configuration management in approximate computation. The main contribution of RAPIDS is its design to address the above concerns through exploiting the different expertise/strengths of the three actors (developers, users, applications) involved. I conduct comprehensive experiments and show that RAPIDS is adaptive and extendable by providing customizable configuration spaces for developers and the support for customizable quality for end-users. It has low overheads and small cross-platform porting costs. I also introduce an extension of RAPIDS, RAPIDS-M (Rapids for Multi-programming), which is the first system that discusses cross-application approximation management. The target is to understand and overcome the challenges in approximation management fundamentally, then let both developers and end-users benefit from approximation with little extra efforts so that a wider audience can accept the technique.
Location: CoRE 305
Committee:

Defense Committee: Prof. Ulrich Kremer (Chair), Prof. Sibren Isaacman (Loyola University), Prof. Rich Martin, Prof. Desheng Zhang, and Dr. Linbin Yu (Facebook)