Jiawei Li
@jiaweili.bsky.social
Postdoc @ Neural dynamics of visual cognition (Cichy lab) @FU_Berlin
interested in language🗣️📖 and its representations in the brain🧠
https://jiawei-liiiii.github.io/
interested in language🗣️📖 and its representations in the brain🧠
https://jiawei-liiiii.github.io/
Reposted by Jiawei Li
Examples: audio before red line = ground-truth prompt; after = AuriStream’s prediction, visualized in the time-frequency cochleagram space.
AuriStream shows that causal prediction over short audio chunks (cochlear tokens) is enough to generate meaningful sentence continuations!
AuriStream shows that causal prediction over short audio chunks (cochlear tokens) is enough to generate meaningful sentence continuations!
August 19, 2025 at 1:12 AM
Examples: audio before red line = ground-truth prompt; after = AuriStream’s prediction, visualized in the time-frequency cochleagram space.
AuriStream shows that causal prediction over short audio chunks (cochlear tokens) is enough to generate meaningful sentence continuations!
AuriStream shows that causal prediction over short audio chunks (cochlear tokens) is enough to generate meaningful sentence continuations!