Teddy

Neuroscience PhD candidate in the Simoncelli lab at NYU. Trying to force computers to learn things the way people do.

[SueYeon Chung @s_y_chung]

🧵0/7
🚨 Spotlight @ICML2025 🚨

Chi-Ning and Hang have been thinking deeply about how feature learning reshapes neural manifolds, and what that tells us about generalization and inductive bias in brains and machines.

They put together the thread below, which I’m sharing on their behalf 👇Enjoy!

[Sonica Saraf (@sonicasaraf.bsky.social) @SarafSonica]

In many brain areas, neuronal tuning is heterogeneous. How does this diversity help behavior? We show how tuning diversity shapes representational geometry and boosts coding efficiency for perception in our new preprint: https://t.co/mVhtABFHkE
(with @s_y_chung & Tony Movshon)

[Teddy @tedyerxa]

Very fun project providing a formal link between MMCR and information theory!

[Rylan Schaeffer @RylanSchaeffer]

🔥🚀Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations🚀🔥

@vclecomte @BerivanISIK @dhruv31415 @carranzamoreno9 @AlyssaUnell @KhonaMikail @tedyerxa

& @sanmikoyejo @ziv_ravid @Andr3yGR @s_y_chung @ylecun

https://t.co/vItFV1oOt3

1/9

[Teddy @tedyerxa]

Corrected github link: https://t.co/z8mkSy3j7B

[Teddy @tedyerxa]

Excited to share our results on Efficient Coding of Natural Images using Maximum Manifold Capacity Representations, a collaboration with @KuangYilun @EeroSimoncelli and @s_y_chung to be presented at #NeurIPS2023

1/n

[Teddy @tedyerxa]

Check out the full paper for more fun, including some empirical results suggesting a mechanism by which augmentation based SSL leads to semantic clustering!

Paper: https://t.co/X0Jzbfn4Qo
Code: https://t.co/ZvraTNPDAr

17/n

[Teddy @tedyerxa]

Also, be sure to check out interesting followup work that formalizes a connection between our MMCR loss function and information theory, from @RylanSchaeffer & colleagues: https://t.co/Z0xUXwTo1D

18/n, n=18

[Rylan Schaeffer @RylanSchaeffer]

Excited to begin announcing our #NeurIPS2023 workshop & conference papers (1/10)!

🔥🚀An Information-Theoretic Understanding of Maximum Manifold Capacity Representations🚀🔥

w/ amazing cast @vclecomte @BerivanISIK @sanmikoyejo @ziv_ravid @Andr3yGR @KhonaMikail @ylecun

1/7