Ken Shirakawa
@kencan7749.bsky.social
Ph.D. candidate in Kyoto university and ATR/ Brain decoding / fMRI / neuroAI / neuroscience
And here’s an experimental podcast-style of paper summary, generated via Notebook LM directed by me!
Link: notebooklm.google.com/notebook/9c8...
Link: notebooklm.google.com/notebook/9c8...
June 13, 2025 at 10:16 AM
And here’s an experimental podcast-style of paper summary, generated via Notebook LM directed by me!
Link: notebooklm.google.com/notebook/9c8...
Link: notebooklm.google.com/notebook/9c8...
Our paper is now accepted at Neural Networks!
This work builds on our previous threads in X, updated with deeper analyses.
We revisit brain-to-image reconstruction using NSD + diffusion models—and ask: do they really reconstruct what we perceive?
Paper: doi.org/10.1016/j.ne...
🧵1/12
This work builds on our previous threads in X, updated with deeper analyses.
We revisit brain-to-image reconstruction using NSD + diffusion models—and ask: do they really reconstruct what we perceive?
Paper: doi.org/10.1016/j.ne...
🧵1/12
Redirecting
doi.org
June 13, 2025 at 9:17 AM
Our paper is now accepted at Neural Networks!
This work builds on our previous threads in X, updated with deeper analyses.
We revisit brain-to-image reconstruction using NSD + diffusion models—and ask: do they really reconstruct what we perceive?
Paper: doi.org/10.1016/j.ne...
🧵1/12
This work builds on our previous threads in X, updated with deeper analyses.
We revisit brain-to-image reconstruction using NSD + diffusion models—and ask: do they really reconstruct what we perceive?
Paper: doi.org/10.1016/j.ne...
🧵1/12
Reposted by Ken Shirakawa
Yukiyasu Kamitani, Misato Tanaka, Ken Shirakawa
Visual Image Reconstruction from Brain Activity via Latent Representation
https://arxiv.org/abs/2505.08429
Visual Image Reconstruction from Brain Activity via Latent Representation
https://arxiv.org/abs/2505.08429
May 14, 2025 at 7:10 AM
Yukiyasu Kamitani, Misato Tanaka, Ken Shirakawa
Visual Image Reconstruction from Brain Activity via Latent Representation
https://arxiv.org/abs/2505.08429
Visual Image Reconstruction from Brain Activity via Latent Representation
https://arxiv.org/abs/2505.08429
Reposted by Ken Shirakawa
One big issue with some of the previous claims are that NSD, the massive 7T fMRI dataset of 1000s of images, might not be the right dataset to test these hypotheses. The reason is that it is built on MSCoCo and has too high similarity between training and test. arxiv.org/abs/2405.10078 16/n
arxiv.org
December 11, 2024 at 10:18 PM
One big issue with some of the previous claims are that NSD, the massive 7T fMRI dataset of 1000s of images, might not be the right dataset to test these hypotheses. The reason is that it is built on MSCoCo and has too high similarity between training and test. arxiv.org/abs/2405.10078 16/n
I’m currently concerned about what the brain’s encoding model predicts. Given that the target brain state is collected under naturalistic condition and the inputs of encoding model derived from a deep neural network, I am not sure what the predictions are actually represent.
November 16, 2024 at 2:08 PM
I’m currently concerned about what the brain’s encoding model predicts. Given that the target brain state is collected under naturalistic condition and the inputs of encoding model derived from a deep neural network, I am not sure what the predictions are actually represent.
