Skip to content
Papers.

Voxtral Realtime research paper by Mistral AI, 2026

Mistral AI · Feb 11, 2026 · Alignment and safety · 6 citations · 28 upvotes · unverified

Read on arXiv

What it shows

Voxtral Realtime is a streaming speech recognition model trained end-to-end for sub-second latency with performance matching offline systems.

UnverifiedHugging Face's summary; not yet checked by hand.

More from Mistral AI

All 4
PaperCitations
Voxtral TTSVoxtral TTS is a multilingual text-to-speech model that generates natural speech from short reference audio using a hybrid architecture combining semantic token generation and flow-matching for acoustic tokens.Multimodal and robotics · Mar 2026 · Unverified0
Ministral 3The Ministral 3 series consists of parameter-efficient dense language models with three sizes (3B, 8B, 14B) and three variants per size, trained using cascade distillation for compute-constrained applications.Reasoning · Jan 2026 · Unverified63
Pixtral 12BPixtral-12B, a 12-billion-parameter multimodal language model, excels in both natural language and image understanding, surpassing larger models and introducing an open-source benchmark for evaluation.Multimodal and robotics · Oct 2024 · Unverified173

Other alignment and safety papers

Topic
PaperCitations
Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI · Mar 202224.3k
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelDPO aligns a model to human preferences with a simple classification loss, no reward model or RL loop.Stanford University · May 202310.6k
Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Anthropic · Dec 20223,721
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Anthropic · Jan 2024578
Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Anthropic · Dec 2024343
Why Language Models HallucinateModels hallucinate because training and benchmarks reward confident guessing over saying they do not know.OpenAI · Sep 2025331
About this paper
Authors
Alexander H. Liu, Andy Ehrenberg, Andy Lo and 131 more
arXiv
2602.11298 · PDF
Venue
arXiv.org
Citations
6, 1 influential · Semantic Scholar
Upvotes
28 · Hugging Face
Lab
Mistral AI · on Companies · on Rounds · on Releases · on Releases

Changes

What changed
Influential citationsfirst count: 1Sep 25, 2026
Citationsfirst count: 6Sep 25, 2026
New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.