# Multimodal LLM Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/multimodal-llm
> Markdown URL: https://aitinkerers.org/technologies/multimodal-llm.md
> Technology record last updated: 2026-02-24T05:39:07Z
> Generated: 2026-10-24T14:09:47Z

Multimodal LLMs (MLLMs) process and reason across diverse data types: text, images, audio, and video, unifying human-like understanding in models like GPT-4V and Gemini.

MLLMs are state-of-the-art large language models that move beyond text-only processing, integrating multiple modalities (data types) for richer context and reasoning. They encode inputs like image pixels, audio waveforms, and text tokens into a shared embedding space, enabling cross-modal analysis. This capability allows for complex tasks: visual question answering (VQA), image captioning, and interpreting charts. Key models, including GPT-4V and Google’s Gemini, exemplify this shift, handling inputs like a photo of a product and a verbal description simultaneously to deliver a coherent, human-like response.

- Official technology site: https://openai.com/research/gpt-4v-system-card
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Pinakes - multimodal note/thought organizer and filer.](https://prague.aitinkerers.org/talks/rsvp_w6HjXKdbuBo)

- Event context: AI Tinkerers Prague: Annual Christmas Meetup 2025 — 2025-12-16 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_w6HjXKdbuBo

### [My best friend is an AI](https://paris.aitinkerers.org/talks/rsvp_uA8S7dyHn_s)

- Event context: Epic Demo night 0.2.1 - Sep 18th, 2025 — 2025-09-18 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_uA8S7dyHn_s

### [Ultravox - OSS Speech LM](https://seattle.aitinkerers.org/talks/rsvp_iCUEDx9LRpw)

- Event context: AI Tinkerers Seattle - June 2024 — 2024-06-07 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_iCUEDx9LRpw

## Related Technologies

- [Containerization](https://aitinkerers.org/technologies/containerization) ([Markdown](https://aitinkerers.org/technologies/containerization.md)) — 3 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 151 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 189 public demos
- [GPT-4o](https://aitinkerers.org/technologies/gpt-4o) ([Markdown](https://aitinkerers.org/technologies/gpt-4o.md)) — 57 public demos
- [Llama 3](https://aitinkerers.org/technologies/llama-3) ([Markdown](https://aitinkerers.org/technologies/llama-3.md)) — 38 public demos
- [Mastra](https://aitinkerers.org/technologies/mastra) ([Markdown](https://aitinkerers.org/technologies/mastra.md)) — 8 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 100 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 686 public demos
- [Speech LLM](https://aitinkerers.org/technologies/speech-llm) ([Markdown](https://aitinkerers.org/technologies/speech-llm.md)) — 1 public demo
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 213 public demos
- [Ultravox](https://aitinkerers.org/technologies/ultravox) ([Markdown](https://aitinkerers.org/technologies/ultravox.md)) — 2 public demos