Pinned Loading

1. cavewoman cavewoman Public

   Caveman prompting, measured. A two-channel evaluation protocol scoring what input and output compression actually cost LLMs in dollars, accuracy, and surface-text fidelity across seven models and f…

   Python 2 1

2. mixviz mixviz Public

   Visualization tool for cross-head mixing in IHA and other non-standard attention architectures.

   JavaScript

3. SensIMG-Bench SensIMG-Bench Public

   SensIMG-Bench is a clinically grounded benchmark for evaluating the visual sensory appropriateness of AI-generated images, with a focus on identifying overstimulation risks for children with autism…

   CSS

4. FASH-iCNN FASH-iCNN Public

   Fashion AI research code for FASH-iCNN: a multimodal system that makes editorial fashion identity inspectable by recovering which house produced a garment, which era it belongs to, and which color …

   Python