Medal, a platform for uploading and sharing video game clips, has spun out a new frontier AI research lab that’s using its trove of gaming videos to train and build foundation models and AI agents ...

This project fine-tunes QWEN-VL models to answer questions from Dora videos using GRPO (Group Relative Policy Optimization). The model learns to combine visual frames and transcript context to provide ...

Spatial reasoning is essential for solving complex tasks in dynamic and high-dimensional environments. However, current training models for spatial tasks are computationally demanding and heavily ...

This organization hosts the repositories for the project LLM Spatial Reasoning: Evaluating and Enhancing Geographic Cognition in Language Models. A core question in GeoAI is whether LLMs have ...