Predicting AI bias using SAEs
Published:
A comparative analysis of how Sparse Autoencoders and MLP activations encode gender information inside LLMs.
Published:
A comparative analysis of how Sparse Autoencoders and MLP activations encode gender information inside LLMs.
Published:
Using Attention to predict image captions with greater accuracy.
Published:
Fine-tuning ViT and ResNet for image classification on Google Cloud.
Published:
A workflow to fetch and summarize job descriptions with Llama 3-70B.
Published:
Voice calling with real-time speech translation and transcription.
Published:
Using simulations to optimize power plant location for minimal externality.
Published:
One-stop shop for managning and reconciling financial trades.
Published:
Using an ensemble of GARCH to predict financial volatility with greater accuracy.