LMMs for AI-Native Wireless Systems - AI/ML webinar
Special Presentation on “LMMs as Universal Foundation Models for AI-Native Wireless Systems”
by Dr. Christo K. Thomas (Virginia Tech, USA)
Hosted by Future Networks Artificial Intelligence & Machine Learning (AIML) Working Group
Date/Time: Thursday, March 7th, 2024 @ 6 PM EST (3 PM PST)
Topic:
Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems
Abstract:
Foundation models such as large language models (LLMs) have recently been touted as game-changers for 6G systems. However, previous efforts on LLMs for wireless networks are limited to directly applying existing language models designed for natural language processing (NLP) applications. Contrary to this, in this talk, we present a comprehensive vision of how to design universal foundation models that are tailored towards the unique needs of next-generation wireless systems, thereby paving the way towards the deployment of artificial intelligence (AI)-native networks. These LMMs are driven by three distinct characteristics: 1) integration of multi-modal sensing data, 2) grounding sensory input via causal reasoning and retrieval-augmented generation (RAG), and 3) instructibility to environmental feedback through logical and mathematical reasoning enabled by neuro-symbolic AI. These attributes are crucial for developing "universal foundation models" capable of addressing interconnected cross-layer networking challenges in AI-native wireless systems while ensuring alignment of objectives across diverse domains. We also discuss preliminary results from experimental evaluation that demonstrate the efficacy of grounding using RAG in LMMs, and showcase the alignment of LMMs with wireless system designs. Furthermore, compared to vanilla LLMs, the enhanced rationale exhibited in the responses to mathematical questions by LMMs demonstrates the logical and mathematical reasoning capabilities inherent in LMMs. Building on those results, we present a sequel of open questions and challenges for LMMs, including intent-based networks, resilient wireless systems, semantic communications, and many more.
Date and Time
Location
Hosts
Registration
- Date: 07 Mar 2024
- Time: 06:00 PM to 07:00 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
- Add Event to Calendar
- Contact Event Host
-
Baw Chng baw@ieee.org - Co-sponsored by IEEE Future Networks
- Starts 16 February 2024 09:54 AM
- Ends 07 March 2024 07:00 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
- No Admission Charge
Speakers
Dr. Christo K. Thomas of Virginia Tech, USA
Biography:
Christo Kurisummoottil Thomas received his BS in Electronics and Communication Engineering from National Institute of Technology, Calicut, India in year 2010, his MS in Telecommunication Engineering from Indian Institute of Science, Bangalore, India in year 2012, and his PhD from EURECOM, France in year 2020. He is currently a postdoctoral fellow at the Electrical and Computer Engineering Department at Virginia Tech. His research interests include semantic communications, statistical signal processing, and artificial general intelligence (AGI)-native wireless systems. From 2012 to 2014, he was a staff design engineer on 4G LTE with Broadcom communications, Bangalore, and from 2014 to 2017, he was a design engineer with Intel corporation, Bangalore. During November 2020 till June 2022, he was a staff engineer on 5G modems with wireless research and development division of Qualcomm Inc., Espoo, Finland. He was a recipient of the best student paper award at IEEE SPAWC 2018, Kalamata, Greece, and also received third prize for his team titled “Learned Chester” ML5G-PHY channel estimation challenge, as part of the ITU AI/ML in 5G challenge, conducted at NCSU, US, 2020.