speaker detail

Abhirup Goswami

Imagineer

company logo

Abhirup is an Imagineer currently working at Fractal, with over 2 years of experience in vision-based deep learning. During his tenure at Fractal, he has worked on multiple projects, developing various models for face antispoofing, poster generation, and more.

He has been a part of the Machine Vision Team, where he was involved in creating image-based solutions for the advertising domain. Prior to this, he completed his BTech from IIT (BHU) and was selected for a Deep Learning Summer School conducted by the University of Genoa, Italy.

Dive deep into the world of AI's latest foundation models in this informative one-hour session. We'll explore the intricacies of large multimodal models (LMMs), their emergent applications, and how they revolutionize content generation. Discover the role of a mixture of experts in enhancing AI capabilities and envision the future of AI agents working alongside these powerful models.

The session covers large multimodal models (LMMs), starting with an introduction to multimodal learning and the architecture of LMMs. It highlights the importance of integrating multiple data types, explores various application scenarios, and discusses evaluation metrics and benchmarks. The session also delves into fine-grained grounding, the mixture of experts' approaches, AI content generation aligned with human intentions, and the role of AI agents in interpreting and interacting with LMMs, with real-world examples throughout.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details