SPS Webinar: Neural Enhanced Belief Propagation for Multiobject Tracking
Date: 7 May 2025
Time: 1:00 PM ET (New York Time)
Presenter(s): Mr. Mingchao Liang
Date: 7 May 2025
Time: 1:00 PM ET (New York Time)
Presenter(s): Mr. Mingchao Liang
Date: 22 April 2025
Time: 11:00 AM ET (New York Time)
Presenter(s): Mr. Julius Richter
Date: 17 April 2025
Time: 11:00 AM ET (New York Time)
Presenter(s): Ms. Karn N. Watcharasupat
Date: 26 March 2025
Time: 8:00 AM ET (New York Time)
Presenter(s): Dr. Nhan Thanh Nguyen, Dr. Nir Shlezinger
Tampere University has several professor positions open related to AI and its applications, covering various areas of signal processing. The positions include a quite substantial starting package, covering funding for multiple research group members. Strong researchers are encouraged to apply! The deadline for applications is 9 March 2025. For more information about the positions, please visit this page.
Large language models(LLMs) have demonstrated increasingly powerful capabilities for reasoning tasks, especially in text. The project aims to explore and advance these capabilities in reasoning across multiple data modalities, including but not limited to text, speech and audio. The integration of multiple modalities can lead to more robust and general systems capable of understading and reasoning about the world in a more human-like manner. The project will involve fine-tuning pre-trained models and developing self-supervised learning techniques to adapt LLMs for multimodal tasks.
Date: 26 February 2025
Time: 10:00 AM ET (New York time)
Presenter(s): Ivan Dokmanić
Date: 23 May 2025
Chapter: Kerala Chapter
Chapter Chair: Reshna Ayoob
Title: Unveil a Better Solution with the Toyota Production System
Date: 2-6 June 2025
Location: College Park, MD, USA
Most current models for analyzing multimodal sequences often disregard the imbalanced contributions of individual modal representations caused by varying information densities, as well as the inherent multi-relational interactions across distinct modalities. Consequently, a biased understanding of the intricate interplay among modalities may be fostered, limiting prediction accuracy and effectiveness.