Papersby Glyph

Notable data and AI papers

Papers627 Labs45

627 papers · 45 labs

Voxtral Realtime research paper by Mistral AI, 2026

Mistral AI · Alignment and safety · Feb 11, 2026 · 10 citations · 28 upvotes · unverified

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

By Alexander H. Liu, Andy Ehrenberg, Andy Lo and 131 more · arXiv 2602.11298 · PDF

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

More from Mistral AI

Multimodal and roboticsUnverifiedMar 26, 2026Voxtral 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.

Mistral AI60 upvotesRead →ReasoningUnverifiedJan 13, 2026Ministral 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.

Mistral AI80 citations66 upvotesRead →Multimodal and roboticsUnverifiedOct 9, 2024Pixtral 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.

Mistral AI190 citations70 upvotesRead →

Alignment and safetyMar 4, 2022Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.

OpenAI25.8k citations26 upvotesRead →Alignment and safetyMay 29, 2023Direct 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 University11.6k citations73 upvotesRead →Alignment and safetyDec 15, 2022Constitutional 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.

Anthropic3,987 citations4 upvotesRead →Alignment and safetyFeb 22, 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsReinforcement Learning from Human Feedback (RLHF) benefits from simpler REINFORCE-style optimization methods over computationally expensive PPO or "RL-free" methods, enhancing performance and reducing cost in large language models.

Cohere804 citations18 upvotesRead →Alignment and safetyJan 10, 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.

Anthropic657 citations30 upvotesRead →Alignment and safetyDec 18, 2024Alignment 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.

Anthropic393 citations10 upvotesRead →

About this paper

Venue: arXiv.org
Citations: 10, 2 influential · Semantic Scholar
Upvotes: 28 · Hugging Face
Lab: Mistral AI · on Companies · on Rounds · on Releases · on Releases

Changes

CitationsNov 9, 2026Citations rose from 9 to 10.

CitationsOct 12, 2026Influential citations rose from 1 to 2.

CitationsOct 12, 2026Citations rose from 8 to 9.

CitationsOct 5, 2026Citations rose from 7 to 8.

CitationsSep 28, 2026Citations rose from 6 to 7.

CitationsSep 25, 2026A first count of 1 influential citations.

CitationsSep 25, 2026A first count of 6 citations.

New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.