Upcoming Events

Welcome to a seminar series on Deep Foundation Models offered by Professor Sriram Ganapathy!

Please fill this registration form: https://forms.office.com/r/k66ab1XTUs

(Registration is free but mandatory)

Lecture 1: 14 November (Friday), 10.30 AM-12.30 PM; Venue: B308, EE dept, IISc / online

Transformer architectures: self-attention, encoder–decoder attention, in-context learning, low-rank adaptation

Self-supervised learning: objectives and loss functions, masked language modelling

Lecture 2: 21 November (Friday), 10.30 AM-12.30 PM; Venue: MMCR, C241, EE dept, IISc / online

Large language models: tokenizers, pre-training and post-training, multimodal alignment, model compression, reinforcement learning for fine-tuning, proximal policy optimisation, benchmarking and evaluation of LLMs

Lecture 3: 28 November (Friday), 10.30 AM-12.30 PM; Venue: MMCR, C241, EE dept, IISc / online

Diffusion models: deep generative models, VAEs and GANs, forward and reverse diffusion, denoising score matching, variational lower bounds, stable diffusion

Instructor biography

Sriram Ganapathy is an Associate Professor in the Department of Electrical Engineering at the Indian Institute of Science. His research interests are in signal processing, machine learning, deep learning, and neuroscience. The research work in his lab – LEAP – is focused on multimodal large language models (LLMs) at scale for analysis, understanding, and generation of multimodal speech, text, and visual signals.