PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

Posted by Caltech

Kavli Affiliate: Wei Gao | First 5 Authors: Qiyao Xue, Xiangyu Yin, Boyuan Yang, Wei Gao, | Summary: Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding of physical realism and deficiency […]


Continue.. PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

Multi-Agent System for Cosmological Parameter Analysis

Posted by dbos Cambridge

Kavli Affiliate: Blake Sherwin | First 5 Authors: Andrew Laverick, Kristen Surrao, Inigo Zubeldia, Boris Bolliet, Miles Cranmer | Summary: Multi-agent systems (MAS) utilizing multiple Large Language Model agents with Retrieval Augmented Generation and that can execute code locally may become beneficial in cosmological data analysis. Here, we illustrate a first small step towards AI-assisted […]


Continue.. Multi-Agent System for Cosmological Parameter Analysis