AI Video Generation Improvements, Code Models Learn Human Preferences, and Manga Gets an AI Makeover

Today's tech frontiers showcase how artificial intelligence is becoming more attuned to human creativity and preferences across multiple domains. From a new system that can turn text and images into fluid videos, to programming models that write code the way humans actually want it, to AI that can generate custom manga stories, we explore how machines are learning to create content that feels more natural and personalized than ever before. Links to all the papers we discussed: STIV: Scalable Text and Image Conditioned Video Generation, STIV: Scalable Text and Image Conditioned Video Generation, Evaluating and Aligning CodeLLMs on Human Preference, Evaluating and Aligning CodeLLMs on Human Preference, DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation, DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation