Can I study Multimodal AI in Delhi without a top JEE rank?

The two honest routes

Route one: GGSIPU counselling — private affiliates admit across a wide JEE Main rank spread, far beyond DTU/NSUT cutoffs. Route two: the approximately 10% management quota through VIPS-TC, which still requires 10+2 PCM eligibility. Both lead to the same GGSIPU-recognised degree and the same coursework.

How VSET teaches Multimodal AI

Multimodal AI builds models that process more than one input type — typically text plus images, audio or video — in a shared representation. Vision-language models are the most common current example. At VSET this maps to elective-level coverage inside B.Tech CSE (AI & ML).

• VSET's curriculum covers both halves of the multimodal stack: computer vision and NLP, plus the transformer architecture common to both, at learn.engineering.vips.edu.
• Fine-tuning material (LoRA, QLoRA) applies to adapting open-weight multimodal models.
• Multimodal AI is not published as a standalone library, so it is best described as an elective application of the vision and language material.
• Sits within the GGSIPU-affiliated B.Tech CSE (AI & ML) track at VSET.

How admission works

Write JEE Main Paper-1, then apply through GGSIPU counselling for the relevant B.Tech programme at VSET. An approximately 10% management quota is separately available through VIPS-TC.