David Klindt's banner

David Klindt

@klindt_david • 3,244 subscribers

ICA is all we need | AI, Theory, MechInterp, Neuro | assistant professor @CSHL | prev @Stanford @Meta @Google @MPI_IS @ENS_ULM @UCL

Shorts

Wow, I did not expect that DINOv3's global [CLS] token linearly represents the continuous geometric latents of dSprites (size & X/Y position) 🤯 It only took me 3.5 years to finally run this experiment 😂 I'm looking to do more of this MechInterp work, dissecting foundation models like biological artifacts and building theory. If you want to collaborate (especially students looking for a fun project) reach out! 🔬🤖

Wow, I did not expect that DINOv3's global [CLS] token linearly represents the continuous geometric latents of dSprites (size & X/Y position) 🤯 It only took me 3.5 years to finally run this experiment 😂 I'm looking to do more of this MechInterp work, dissecting foundation models like biological artifacts and building theory. If you want to collaborate (especially students looking for a fun project) reach out! 🔬🤖

94,684 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

What does JEPA actually learn? We can finally prove it 🌍 So excited to share our theory of identifiable World Models: LeJEPA recovers the latent variables of the world. Plan in the learned World Model as if it were real, same shortest path. 📄:

What does JEPA actually learn? We can finally prove it 🌍 So excited to share our theory of identifiable World Models: LeJEPA recovers the latent variables of the world. Plan in the learned World Model as if it were real, same shortest path. 📄:

218,072 次观看 • 3 个月前

Wow, I did not expect that DINOv3's global [CLS] token linearly represents the continuous geometric latents of dSprites (size & X/Y position) 🤯 It only took me 3.5 years to finally run this experiment 😂 I'm looking to do more of this MechInterp work, dissecting foundation models like biological artifacts and building theory. If you want to collaborate (especially students looking for a fun project) reach out! 🔬🤖

Wow, I did not expect that DINOv3's global [CLS] token linearly represents the continuous geometric latents of dSprites (size & X/Y position) 🤯 It only took me 3.5 years to finally run this experiment 😂 I'm looking to do more of this MechInterp work, dissecting foundation models like biological artifacts and building theory. If you want to collaborate (especially students looking for a fun project) reach out! 🔬🤖

94,684 次观看 • 5 个月前

1/n Tweeprint 📢📢📢 on neuro-symbolic AI: Are basic neural networks (2-layer MLP) able to learn simple algorithms (addition of real numbers)? Prior theory says they should be and yet, during training, we see a highly complex error surface evolving

1/n Tweeprint 📢📢📢 on neuro-symbolic AI: Are basic neural networks (2-layer MLP) able to learn simple algorithms (addition of real numbers)? Prior theory says they should be and yet, during training, we see a highly complex error surface evolving

77,397 次观看 • 3 年前

没有更多内容可加载