MoST: One Open-Source Model for Speech + Text

Kari Jaaskelainen

16 Jan 2026 — 1 min read

Meet MoST, a fully open-source AI that understands speech and text in one model. Instead of treating audio and words the same, MoST uses a Modality-Aware Mixture of Experts (MAMoE) to send each token to the right specialists.

Modality-specific experts learn the unique patterns of audio and text.
Shared experts help knowledge flow across both, boosting cross-modal skills.
Efficient training pipeline: post-train on ASR/TTS, then fine-tune on speech-text instructions — all from open datasets.

Results: MoST beats similarly sized models on ASR, TTS, audio language modeling, and spoken question answering. Ablations show routing + shared experts drive the gains.

Why it matters: a practical path to assistants that listen, read, and reply more accurately—using only open data.

Paper: https://arxiv.org/abs/2601.10272 | Code & data: https://github.com/NUS-HPC-AI-Lab/MoST

Paper: https://arxiv.org/abs/2601.10272v1

Register: https://www.AiFeta.com

#AI #SpeechAI #Multimodal #MixtureOfExperts #OpenSource #ASR #TTS #LLM #NLP #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A