TechFeed

归档 · 2024 年 12 月

2024 年 12 月 2 篇 / 2 天 ← 回到主页

12月24日周二2024-12-241 篇

Qwen
QVQ:以智慧看世界QVQ: To See the World with Wisdom

GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD 语言与视觉在人的大脑中交织,塑造我们感知和理解周围世界的方式。我们的推理能力深植于语言思维和视觉记忆——但当我们将…

GITHUB HUGGING FACE MODELSCOPE KAGGLE DEMO DISCORD Language and vision intertwine in the human mind, shaping how we perceive and understand the world around us. Our ability to reason is deeply rooted in both linguistic thought and visual memory - but what happens when we extend t…

12月12日周四2024-12-121 篇

EleutherAI
在相同数据上训练的 SAE 并未学习相同的特征SAEs trained on the same data don’t learn the same features

在本文中,我们展示了当两个 TopK SAE 在相同数据、相同批次顺序下训练,但使用不同的随机初始化时,第一个 SAE 中有许多潜在特征在第二个中没有接近的对应,反之亦然。事实上,仅在…

In this post, we show that when two TopK SAEs are trained on the same data, with the same batch order but with different random initializations, there are many latents in the first SAE that don't have a close counterpart in the second, and vice versa. Indeed, when training only a…

归档按月浏览全部历史