Pinned Loading

1. One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

   Python 4.4k 640

2. 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

   Python 3.4k 209

3. A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

   Python 823 39

4. Agentic LaTeX Writer - Local-first editor for AI-assisted academic writing

   TypeScript 265 21

5. [CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models

   Python 294 16

6. Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

   Python 72 4