Close Menu
  • AI
  • Content Creation
  • Tech
  • Robotics
AI-trends.todayAI-trends.today
  • AI
  • Content Creation
  • Tech
  • Robotics
Trending
  • Potential Cognition AI Spherical Would Elevate $2B-Plus at $75B Valuation – Unite.AI
  • OpenRouter Cuts Three Suppliers After AI Immediate Publicity Findings – Unite.AI
  • A Group of Researchers from Columbia and CertiK Introduce TensorLean for Formal Verification of GPU Kernels
  • Collectively AI Discloses Immediate Leak After Coding Agent Uncovered Credential – Unite.AI
  • Dragos Finds Immediate Leaks and Stolen Keys in AI Provide Chains
  • Lean and Mathlib Communities Certify Claude-Assisted Riemann Proof – Unite.AI
  • AWS Routes HyperPod Inference Throughout Areas From One Endpoint – Unite.AI
  • DailyAI Briefing: A Lean-checked Riemann proof, plus 4 extra
AI-trends.todayAI-trends.today
Home»Tech»Kyutai Releases Voice of Motive: A Speech-Native Mannequin that Solves Spoken Math with Reinforcement Studying

Kyutai Releases Voice of Motive: A Speech-Native Mannequin that Solves Spoken Math with Reinforcement Studying

Tech By Gavin Wallace23/09/20264 Mins Read
Facebook Twitter LinkedIn Email
DeepSeek Releases R1-0528: An Open-Source Reasoning AI Model Delivering Enhanced
DeepSeek Releases R1-0528: An Open-Source Reasoning AI Model Delivering Enhanced
Share
Facebook Twitter LinkedIn Email

Kyutai has launched Voice of Motive, 2 open-weight speech-to-speech fashions that remedy math issues out loud. Each begin from GLM-4-Voice-9B and add supervised fine-tuning (SFT) and reinforcement studying (RL). There isn’t a transcription step and no separate textual content LLM within the loop. On spoken GSM8K, accuracy climbs from 27.3% for the bottom mannequin to 77.1%.

Is it deployable? Sure, for self-hosting. Kyutai ran each BF16 checkpoints on a single H100. You additionally want the GLM-4-Voice repo for its speech tokenizer and decoder. Weights inherit the GLM-4-Voice license, and no Hugging Face inference supplier hosts them but.

Why Speech Fashions Lag on Math

Cascaded pipelines (speech-to-text, textual content LLM, text-to-speech) nonetheless lead on reasoning. Nevertheless, every stage provides latency, and the pipeline loses paralinguistic cues like tone. Speech-native fashions should emit audio at common intervals to remain interactive. That limits what number of hidden reasoning tokens they will afford.

Base GLM-4-Voice scores 27.3% on GSM8K. The sooner STITCH methodology raised that to 58.7% by including reasoning chunks. The analysis group name their work the primary software of RL to math reasoning in speech-native fashions.

How the Coaching Works

GLM-4-Voice interleaves its output: 13 textual content tokens, then 26 audio tokens, repeating.

  • Stage-1 SFT: Coaching makes use of 150,616 issues from Orca-Math. Qwen3-235B rewrote every downside for speech. Kyutai’s DSM TTS then voiced them in lots of voices. SFT alone lifts GLM-4-Voice from 27.3% to 61.7%.
  • Stage-2 RL: For every spoken query, the mannequin samples 4 replies at temperature 0.9. A decide, Qwen3-235B-A22B-2507, scores the decoded textual content with a binary reward. The decide by no means sees the reference reply. On 100 hand-checked instances, it agreed with people 88% of the time.

Rewards are centered inside every group, forming a group-relative REINFORCE goal. It’s associated to GRPO however drops PPO clipping and KL regularization. Coaching ran on 16 H100 GPUs, with 1,500 RL updates.

2 design decisions matter most:

  • Temperature correction: Logits are divided by the sampling temperature earlier than the log-softmax within the loss. With out it, GSM8K collapsed from 65.5% to 12.3%.
  • Audio-token merging: At every audio place, all audio-vocabulary possibilities are summed into 1 summary token. The loss asks solely whether or not audio got here subsequent, not which audio token. The paper proves this estimator is unbiased and lower-variance below a value-invariance assumption.

Interactive Explainer

‘;d.appendChild(lab);d.appendChild(pr);});
q(‘#kvr-lkey’).fashion.background=repair?’#7DB7FF’:’#FF6B6B’;
q(‘#kvr-tv’).textContent=”Mismatch (total variation): “+(television*100).toFixed(1)+’%’;
q(‘#kvr-tnote’).textContent=repair?’Logits are divided by T earlier than the log-softmax within the RL loss, so the gradient is computed for the precise coverage that produced the samples.’:’Samples are drawn from softmax(z / T) however scored below softmax(z). The gradient estimator not matches the sampler. Within the paper this collapsed GSM8K from 65.5% to 12.3%.’;
resize();}
perform drawAbl(){var rows=[[‘Default setup’,’merged audio, correction on, group 4′,65.5,’65.5 u00b1 1.1′,’ours’],[‘Group size 8′,”,67.0,’67.0’,”],[‘Loss on all tokens’,”,64.4,’64.4′,”],[‘Loss on text tokens only’,”,63.8,’63.8′,”],[‘No temperature correction’,”,12.3,’12.3′,fix?”:’hot’]];paint(q(‘#kvr-abl’),rows);}
q(‘#kvr-T’).addEventListener(‘enter’,temp);
seg(‘kvr-fix’,perform(b){repair=b.getAttribute(‘data-f’)===’1′;temp();drawAbl();});
temp();

/* slide 4: outcomes */
var dec=”paper”;
perform drawRes(){var P=dec===’paper’;var rows=[
[‘PersonaPlex’,’8B, full-duplex’,3.2,’3.2′,”],
[‘GLM-4-Voice (base)’,’9B’,27.3,’27.3′,”],
[‘STITCH (Chiang et al.)’,’9B, reasoning chunks’,58.7,’58.7′,”],
[‘Voice of Reason’,’9B, direct answers’,P?65.5:70.3,P?’65.5 u00b1 1.1′:’70.3′,’ours’],
[‘Voice of Reason (Stitch)’,’9B, silent reasoning’,P?74.8:77.1,P?’74.8 u00b1 1.1′:’77.1′,’ours’],
‘Prime traces, not matched on dimension or structure’,
[‘Qwen2.5-Omni’,’7B, text output’,84.7,’84.7′,”],
[‘Qwen3-Omni’,’30B, text output’,94.6,’94.6′,”],
[‘Cascaded ASR, LLM, TTS, ASR’,’Gemma-4-31B-IT + Kokoro’,95.7,’95.7′,”]];paint(q(‘#kvr-res’),rows);}
perform paint(el,rows){el.innerHTML=”;var fills=[];rows.forEach(perform(r){if(typeof r===’string’){var s=doc.createElement(‘div’);s.className=”kvr-sep”;s.textContent=r;el.appendChild(s);return;}
var n=doc.createElement(‘div’);n.className=”kvr-rname”;n.innerHTML=r[0]+(r[1]?’‘+r[1]+’‘:”);
var tr=doc.createElement(‘div’);tr.className=”kvr-track”;var f=doc.createElement(‘div’);f.className=”kvr-fill “+r[4];tr.appendChild(f);
var v=doc.createElement(‘div’);v.className=”kvr-val”;v.textContent=r[3]+’%’;var row=doc.createElement(‘div’);row.className=”kvr-rrow”;row.appendChild(n);row.appendChild(v);row.appendChild(tr);el.appendChild(row);fills.push([f,r[2]]);});
requestAnimationFrame(perform(){requestAnimationFrame(perform(){fills.forEach(perform(x){x[0].fashion.width=x[1]+’%’;});});});resize();}
seg(‘kvr-dec’,perform(b){dec=b.getAttribute(‘data-d’);drawRes();});
})();

AI ATH math Speech
Share. Facebook Twitter LinkedIn Email
Avatar
Gavin Wallace

Related Posts

A Group of Researchers from Columbia and CertiK Introduce TensorLean for Formal Verification of GPU Kernels

22/11/2026

OpenAI Ships GPT-Stay-1.1 for Voice Brokers, Cuts Idle Value to $0.02/Min

21/11/2026

Meet Pondering Machines Inkling 2 Mini: 26B Looped MoE Runs on a 32GB Mac

21/11/2026

Baseten Releases Bison-1 and Groundhog-1, Topping Choice Mannequin Index

21/11/2026
Top News

The WIRED roundup includes Alpha School, Grokipedia and Real Estate AI Videos

Apple plans to continue selling iPhones after it turns 100

Free ChatGPT Flatters Much less however Makes Extra Errors

Gemini Spark in Action: My boyfriend was friend-zoned by Gemini after I gave it access to my life.

AI will replace Nuclear Treaties. You’re still not scared?

Load More
AI-Trends.Today

Your daily source of AI news and trends. Stay up to date with everything AI and automation!

X (Twitter) Instagram
Top Insights

Designing Scalable Interactive Visualizations With Reflex XY : Compositions, Renderings in Million Points, Streamings, Custom Marks and Export

08/08/2026

Ben Bernstein, Supervisor of Cybersecurity Advisors at Huntress – Interview Sequence – Unite.AI

19/09/2026
Latest News

Potential Cognition AI Spherical Would Elevate $2B-Plus at $75B Valuation – Unite.AI

22/11/2026

OpenRouter Cuts Three Suppliers After AI Immediate Publicity Findings – Unite.AI

22/11/2026
X (Twitter) Instagram
  • Privacy Policy
  • Contact Us
  • Terms and Conditions
© 2026 AI-Trends.Today

Type above and press Enter to search. Press Esc to cancel.