State of AI Podcast • 003

Contents

1. FullStack Bench: Evaluating LLMs as Full Stack Coders

2. ZS4C: Zero-Shot Synthesis of Compilable Code for Incomplete Code Snippets using LLMs

3. Monet: Mixture of Monosemantic Experts for Transformers

4. Towards Foundation Models for 3D Vision: How Close Are We?

5. Diverse Score Distillation

6. Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthes…