EPISODE · Jul 8, 2025 · 8 MIN
深入剖析GLM-4.1V-Thinking：迈向通用多模态推理的新篇章
from AI Podcast · host weedge
在本期节目中，我们将深入探讨一款名为GLM-4.1V-Thinking的全新视觉语言模型。我们将详细解析其独特的以推理为核心的训练框架，包括大规模预训练、监督微调，以及创新的“带课程采样的强化学习”（RLCS）技术。我们将讨论该模型如何以90亿的参数规模，在多项基准测试中挑战甚至超越体量远超于它的模型（如72B模型和GPT-4o），并探讨其在跨领域泛化方面的惊人表现、面临的挑战与未来的发展方向。
Embed this episode
Ready to play
深入剖析GLM-4.1V-Thinking：迈向通用多模态推理的新篇章
0:00
8:21
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.
Frequently Asked Questions
How long is this episode of AI Podcast?
This episode is 8 minutes long.
When was this AI Podcast episode published?
This episode was published on July 8, 2025.
Can I download this AI Podcast episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!