Jingwen Liang, Gengyu Wang

Daily Paper Cast

Sintonizzati per episodi quotidiani che esplorano i migliori articoli di ricerca sull'IA, completi di copioni e audio generati dall'IA. Unisciti alla conversazione e condividi i tuoi pensieri con noi!

Listen on Apple Podcasts

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

E356 • 22 mins • Jan 9, 2025

Episodi recenti

Jan 9, 2025

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

E356 • 22 mins

Jan 9, 2025

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

E355 • 23 mins

Jan 9, 2025

Cosmos World Foundation Model Platform for Physical AI

E354 • 26 mins

Jan 9, 2025

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

E353 • 22 mins

Jan 9, 2025

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

E352 • 23 mins

Lingua
Inglese
Paese
India
Feed Host