Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
22:01
Offline Reinforcement Learning for LLM Multi-Step Reasoning
1:49:55
How To Speak Fluently In English About Almost Anything
29:10
smolagents - NOVO Framework de Agentes do HuggingFace
15:36
Diving into Self Evolving Training for Multimodal Reasoning
23:15
YuLan-Mini: An Open Data-efficient Language Model
50:42
Nova descoberta de IA: transição de fase na aprendizagem (sem ajustes finos)
39:56
Além do RAG: Nova aprendizagem contínua de LLM com InCA
18:14