Klemen Kotar
@klemenkotar.bsky.social
CS PhD Candidate at Stanford NeuroAI Lab
Reposted by Klemen Kotar
Humans largely learn language through speech. In contrast, most LLMs learn from pre-tokenized text.
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
August 19, 2025 at 1:12 AM
Humans largely learn language through speech. In contrast, most LLMs learn from pre-tokenized text.
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
In our #Interspeech2025 paper, we introduce AuriStream: a simple, causal model that learns phoneme, word & semantic information from speech.
Poster P6, tomorrow (Aug 19) at 1:30 pm, Foyer 2.2!
Reposted by Klemen Kotar
Joint with @klemenkotar.bsky.social, and with @evfedorenko.bsky.social @dyamins.bsky.social
Paper: www.isca-archive.org/interspeech_...
Website: tukoresearch.github.io/auristream-s... (with audio examples)
HuggingFace: huggingface.co/TuKoResearch...
Paper: www.isca-archive.org/interspeech_...
Website: tukoresearch.github.io/auristream-s... (with audio examples)
HuggingFace: huggingface.co/TuKoResearch...
ISCA Archive - Representing Speech Through Autoregressive Prediction of Cochlear Tokens
www.isca-archive.org
August 19, 2025 at 1:12 AM
Joint with @klemenkotar.bsky.social, and with @evfedorenko.bsky.social @dyamins.bsky.social
Paper: www.isca-archive.org/interspeech_...
Website: tukoresearch.github.io/auristream-s... (with audio examples)
HuggingFace: huggingface.co/TuKoResearch...
Paper: www.isca-archive.org/interspeech_...
Website: tukoresearch.github.io/auristream-s... (with audio examples)
HuggingFace: huggingface.co/TuKoResearch...
Reposted by Klemen Kotar
What are the organizing dimensions of language processing?
We show that voxel responses during comprehension are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals
We show that voxel responses during comprehension are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals
May 23, 2025 at 5:00 PM
What are the organizing dimensions of language processing?
We show that voxel responses during comprehension are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals
We show that voxel responses during comprehension are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals
Reposted by Klemen Kotar
Sadly couldn’t make it to ICLR Re-Align, but check out @klemenkotar.bsky.social and my prelim work on ‘model connectomes’—sparse initializations derived across LLM generations to enable efficient learning in low-data regimes, loosely inspired by evolution and lifetime learning.
shorturl.at/PNXXW
shorturl.at/PNXXW
April 28, 2025 at 8:54 PM
Sadly couldn’t make it to ICLR Re-Align, but check out @klemenkotar.bsky.social and my prelim work on ‘model connectomes’—sparse initializations derived across LLM generations to enable efficient learning in low-data regimes, loosely inspired by evolution and lifetime learning.
shorturl.at/PNXXW
shorturl.at/PNXXW