← Back to all news
arXiv AI October 15, 2026 By Worasait Suwannik

Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

  • llms
  • rag
  • safety

One email a morning, machine-written

One email a day, machine-written, one click to leave. We never share your address.

Related stories

arXiv Computation and Language
Sep 15

Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech

arXiv:2609.14817v1 Announce Type: new Abstract: In Yor\`ub\'a, pitch alone separates \d{o}k\d{o} (husband, Mid), \d{o}k\d{\`o} (vehicle, Low), and \d{o}k\d{\'o} (hoe, High) -- the diacritics ARE the...

By Moses Daudu, Adeola Enitan Bamidele, Honor-Jesus Bezaleel
fine-tuningmultimodal
More like this →
arXiv AI
Sep 30

Break Step: Recursive Training Resonates with Replayed Sampling Noise

arXiv:2609.11149v3 Announce Type: replace-cross Abstract: How fast does a language model degrade when trained on its own outputs? Theory traces it to gradually accumulating errors, while experiments...

By Yangze Liu, Zhongyi Han
llmsfine-tuning
More like this →
arXiv Computation and Language
3d ago

GRAFT: Restoring the Missing Sampling Interface in Continuous Diffusion Language Models

arXiv:2610.29136v1 Announce Type: new Abstract: Continuous diffusion language models generate a whole sequence in parallel, never drawing a single word at any intermediate step; only the final step t...

By Haoning Yang, Lili Pan
llmsragdiffusion
More like this →
arXiv Computation and Language
Sep 17

Myovox: Reading Speech from the Muscles of the Face

arXiv:2609.17548v1 Announce Type: new Abstract: Myovox, from myo (muscle) and vox (voice), decodes open-vocabulary English text from 31-channel surface electromyography (sEMG) recorded from the muscl...

By Varshith Madishetty
llmsragfine-tuningefficiencymultimodal
More like this →
arXiv Machine Learning
Jul 24

GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus

arXiv:2607. 20443v1 Announce Type: cross Abstract: We release GLAN-QnA-KR, a 303,581-row openly redistributable Korean instruction-QA corpus produced via the seedless taxonomy-driven GLAN synthesis pipeline with Microsoft's Phi-3.

By Daekeun Kim
More like this →
arXiv Computation and Language
Sep 17

Planning or Improvisation? Stress-Testing the Poetry Planning Site on Open Models and Open Cross-Layer Transcoders

arXiv:2609.18440v1 Announce Type: new Abstract: Lindsey et al. (2025) report that Claude 3.5 Haiku plans rhymes: features for candidate rhyme words are active on the newline before a line is written,...

By \'Eric Jacopin
llms
More like this →
About Pricing API Newsletter Sources Privacy Terms Refunds Accessibility Provider info Contact RSS

The Flow links to publishers and never republishes their articles. Summaries are machine-generated.

v1.1.0 · 5f852ea