Intellectual Property India Publishes Patent Application for Processing Multimodal Prompts Using Text-Only Large Language Models

MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202647113864 A) filed by Google LLC on September 23, 2026, for Processing Multimodal Prompts Using Text-Only Large Language Models.

Inventor includes Wang, Quan.

The application for the patent was published on September 25, 2026, under issue no. 39/2026.

Abstract: A multimodal system (150) includes a multimodal encoder (160), a vector quantization model (170), and a text-only large language model (LLM) (180). The multimodal encoder is configured to receive, as input, a multimodal input (106) for a prompt (184), and generate, based on the multimodal input, a sequence of embeddings (162). The vector quantization model is configured to receive, as inp...