From mgoswami at andrew.cmu.edu Mon Mar 11 17:43:35 2024 From: mgoswami at andrew.cmu.edu (Mononito Goswami) Date: Mon, 11 Mar 2024 17:43:35 -0400 Subject: Papers accepted at the AAAI 2024 Spring Symposium on Clinical Foundation Models Message-ID: Hi all, We accepted 32 high-quality submissions at the AAAI 2024 Spring Symposium on Clinical Foundation Models that we are organizing later this month. There's work relevant to multiple funded projects at the lab: AID-ART, ORCA to name a few. Best regards, Mononito & Rachel P.S. Thanks Ceci for helping us make these decisions! Thanks to Autonians who served as reviewers, and huge thanks to Vedant, Jessie and Angela for helping us review at the last hour! -------------- next part -------------- An HTML attachment was scrubbed... URL: From awd at cs.cmu.edu Mon Mar 18 16:51:49 2024 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Mon, 18 Mar 2024 16:51:49 -0400 Subject: Fwd: Thesis Defense - April 2, 2024 - Cristian Challu - Representing Time: Towards Pragmatic Multivariate Time Series Modeling In-Reply-To: <9021cb66-c0c7-40bb-a630-6dfe50aca2f1@andrew.cmu.edu> References: <9021cb66-c0c7-40bb-a630-6dfe50aca2f1@andrew.cmu.edu> Message-ID: A big day coming up for the Lab, please mark your calendars and come listen to an exciting talk by Cristian! Cheers Artur ---------- Forwarded message --------- From: Diane Stidle Date: Mon, Mar 18, 2024 at 3:29?PM Subject: Thesis Defense - April 2, 2024 - Cristian Challu - Representing Time: Towards Pragmatic Multivariate Time Series Modeling To: ml-seminar at cs.cmu.edu , *Thesis Defense* Date: April 2, 2024 Time: 11:00am (EDT) Place: NSH 3305 & Remote PhD Candidate: Cristian Challu *Title: Representing Time: Towards Pragmatic Multivariate Time Series Modeling* Abstract: Time series models are specialized in learning temporal dependencies among observations and interactions between features in a data stream. During the last decade, the unprecedented success of deep learning models on Computer Vision and Natural Language Processing has steadily permeated to time series tasks. From Recurrent Neural Networks to Transformers, new advancements in architectural design improved capabilities and performance. Despite this success, I identify several challenges to adopting current state-of-the-art methods, including handling distribution shifts and missing data, computational complexity, and interpretability. The success of DL models is usually explained by their ability to automatically discover helpful data representations. Multivariate time series models involve high-dimensional objects with numerous time series and temporal observations. However, they often exhibit strong temporal dependencies and inter-feature relations. In this thesis, I propose to design algorithms for forecasting and anomaly detection tasks that leverage these dependencies to induce efficient learning of representations that satisfy desirable properties that can (i) improve the models' performance, (ii) improve robustness by favoring domain adaptation, and (iii) reduce overparameterization to improve scalability. The completed work includes three parts, presenting seven models and algorithms that achieve SoTA performance in various tasks while addressing key adoption challenges. In the first part, I explore the dynamic latent space principle and design latent temporal representations to make robust anomaly detection and forecasting models. In the second part, I present a novel scalable and interpretable model for multi-step forecasting based on a non-linear frequency decomposition with connections to Wavelet theory. It also features two extensions on using multivariate exogenous covariates for high-impact domains, including energy and healthcare. Finally, in the third part, I present a large-scale study on enabling conditions, on both model design and data characteristics, for transferability of pre-trained models on time series tasks. *Thesis Committee:* Artur Dubrawski, Chair Roni Rosenfeld Barnabas Poczos Ying Nian Wu (UCLA) Link to Draft Document: https://drive.google.com/file/d/17luIWYw3bLRYe-BuXn1QstlQad0ozXu8/view?usp=sharing Zoom meeting link: https://cmu.zoom.us/j/99919622332?pwd=Y0E0ZU0xMCswbmFyTXBzNDRuK05mZz09 Meeting ID: 999 1962 2332 Passcode: 902254 -- Diane Stidle PhD Program Manager Machine Learning Department Carnegie Mellon Universitystidle at andrew.cmu.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From awd at cs.cmu.edu Wed Mar 20 16:40:52 2024 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Wed, 20 Mar 2024 16:40:52 -0400 Subject: Fwd: [AsilomarSSC] CFP: 2024 Asilomar Conference on Signals, Systems, and Computers In-Reply-To: <2e388fad-4303-435c-8268-738e0d140c4b@Spark> References: <9fea01b6-7043-4558-bf11-443bac41e761@Spark> <2e388fad-4303-435c-8268-738e0d140c4b@Spark> Message-ID: This is a really good venue to consider. Artur ---------- Forwarded message --------- From: Linda DeBrunner via AsilomarSSC Date: Wed, Mar 20, 2024, 4:23?PM Subject: [AsilomarSSC] CFP: 2024 Asilomar Conference on Signals, Systems, and Computers To: Linda DeBrunner via AsilomarSSC The Asilomar Conference on Signals, Systems, and Computers will be held Oct. 27-30, 2024. We hope you will consider submitting a paper. *Extended Summaries are due for consideration by May 1, 2024. *Students that are first authors are encouraged to participate in the Student Paper Contest, which requires full paper submissions at this time. Details of the student paper contest are given on the conference website. Submissions will be accepted starting April 1, 2024. Notifications of acceptance will be mailed by mid-July 2024. Full final papers are due shortly after the conference and published in early 2025. The Call for Papers is attached. Updates will be posted on the conference website: https://www.asilomarsscconf.org/. *Authors are invited to submit papers in the following areas:* *A. Communication Systems*: 1. Modulation and Coding, 2. Channel Estimation and Equalization, 3. ML for Communications, 4. Full Duplex, 5. JC&S, 6. Ultra-Low Latency, 7. Physical Layer Security & Privacy, 8. Underwater Communications, 9. Wireline & Optical Communications, 10. Satellite Communications, 11. Communication Schemes for IoT, V2V, etc. 12. 6G and Beyond *B. MIMO Communications and Signal Processing: *1. Single- and Multi-User MIMO, 2. Massive MIMO, 3. MIMO Channel Estimation 4. Cooperation & Relaying, 5. Interference Management & Awareness, 6. mmWave and THz, 7. Cell-Free Systems, 8. Reconfigurable Intelligent Surfaces *C. Networks and Graphs: *1. Network Information Theory, 2. Distributed Optimization & Algorithms, 3. Graph Signal Processing, 4. Machine Learning over Graphs, 5. Federated Learning, 6. Wireless Networks, 7. IoT, 8. Social Networks and Network Science, 9. Data Networks & Computational Offloading, 10. Transportation, UAV & V2V Networks, 11. Power Networks & Smart Grids *D. Adaptive Systems, Machine Learning, and Data Analytics*: 1. Adaptive Filtering, 2. Adaptive and Cognitive Systems, 3. Estimation and Inference, 4. Compressive Sensing and Sparse Recovery, 5. Models for High-Dimensional Large-Scale Data, 6. Optimization, 7. Online Learning and Regret Minimization, 8. Learning Theory and Algorithms, 9. Self- and Semi-supervised Learning, 10. Deep Learning, 11. Reinforcement Learning *E. Array Processing and Multisensor Systems*: 1. Source Localization and Separation, 2. DoA Estimation, 3. Tensor Models and Processing, 4. ML for Array Processing and Multisensor Systems, 5. Sparse Sensor Arrays, 6. Robust Methods, 7. Applications (Imaging, MIMO Radar, JC&S, Sonar, Microphone Arrays, etc.) *F. Biomedical Signal and Image Processing*: 1. Molecular and Medical Imaging, 2. Computational Imaging, 3. Neuroengineering, 4. Processing of Physiological Signals, 5. Bioinformatics and Computational Biology, 6. Image Registration and Multimodal Imaging, 7. Functional Imaging, 8. Brain Machine Interfaces, 9. Neural Signal Processing, 10. Computational Neuroscience *G. Architectures and Implementation*: 1. Computer Arithmetic and Algorithms, 2. Algorithm and Architecture Co-optimization, 3. Hardware Accelerators, 4. Reconfigurable Processing, 5. Multi- core, Many-core, and Distributed Systems, 6. Architectures for ML, 7. In-Memory Processing, 8. Cyber-Physical Systems, 9. Mixed-Signal Processors, 10. Testbeds, 11. Emerging Technologies *H. Speech, Image and Video Processing*: 1. Speech Coding, 2. Speech Recognition, 3. Audio Coding, 4. Document Processing, 5. Models for Speech & Image Processing, 6. Image & Video Coding, 7. Learning and Autonomous Systems, 8. Natural Language Processing, 9. Computer Vision, Image and Video Analysis, 10. Image & Video Forensics, 11. Biometrics & Security, 12. Hybrid Imaging Systems Dr. Linda S. DeBrunner Electrical & Computer Engineering FAMU-FSU College of Engineering Florida State University -- AsilomarSSC mailing list AsilomarSSC at lists.fsu.edu To Unsubscribe: https://lists.fsu.edu/mailman/listinfo/asilomarssc -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: call24_final.pdf Type: application/pdf Size: 161730 bytes Desc: not available URL: From awd at cs.cmu.edu Tue Mar 26 12:05:05 2024 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 26 Mar 2024 09:05:05 -0700 Subject: Fwd: Distinguished Lecture from Jodi Forlizzi of Carnegie Mellon University, April 4, 2024 from 3:00-4:00 PM EDT In-Reply-To: References: Message-ID: Quite relevant online NSF talk by a good friend of the Auton Lab. Artur ---------- Forwarded message --------- From: Nilsen, Wendy J. Date: Tue, Mar 26, 2024, 8:02?AM Subject: Distinguished Lecture from Jodi Forlizzi of Carnegie Mellon University, April 4, 2024 from 3:00-4:00 PM EDT To: Join the Directorate for Computer and Information Science and Engineering (CISE) and the Division of Information and Intelligent Systems (IIS) for a Distinguished Lecture from Jodi Forlizzi of Carnegie Mellon University. This event will take place virtually on Zoom. The lecture is on April 4, 2024 from 3:00-4:00 PM EDT and will be immediately followed by a Q&A session at 4:00 PM EDT. If you plan to attend, please pre-register to this lecture: https://nsf.zoomgov.com/j/1611338097?pwd=N0tXVEliQityV04zZ25kbFUwcDVuZz09 *The Design of Socially Responsible AI:* What we design is changing; therefore, how we design is also changing. In this talk, I will set the context for the role of design in creating purposeful and pragmatic technology, both historically and today. I will then highlight some of our research showing the impact of design in creating, developing, and deploying AI and autonomous systems, with the goal of creating better social systems, better economic relations, and a better world in which to live. *Biography* Jodi Forlizzi, *PhD* Dr. Jodi Forlizzi is the Herbert A. Simon Professor of Computer Science and Human-Computer Interaction in the School of Computer Science at Carnegie Mellon University. She is also a Faculty Lead in Responsible AI in the Block Center for Technology and Society and the Associate Dean of Diversity, Equity, and Inclusion in the School of Computer Science. Jodi has advocated for design research in all forms, mentoring peers, colleagues, and students in its structure and execution, and today it is an important part of the HCI community. Jodi studies the ethical impacts of human interaction with AI systems in front-line service industries including healthcare and hospitality. She also develops methods and tools to ensure that product developers can mitigate ethical harms and bias during product development. She recently testified to the US Senate in one an AI Innovation Briefing and collaborates closely with the AFL-CIO Tech Institute. Wendy J. Nilsen, PhD Deputy Division Director Information and Intelligent Systems Computer & Information Science & Engineering Directorate National Science Foundation 2415 Eisenhower Avenue Alexandria, Virginia 22314 Tel: 703-292-2568 Email: wnilsen at nsf.gov Want to know more about IIS? Join our listserv Please click unsubscribe to unsubscribe from the list. When the new email window opens, please click send without adding or making any modifications to the email. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.jpg Type: image/jpeg Size: 57267 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image002.jpg Type: image/jpeg Size: 4968 bytes Desc: not available URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image002.jpg Type: image/jpeg Size: 4968 bytes Desc: not available URL: