Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Ministral 3 research paper by Mistral AI, 2026

Mistral AI · Reasoning · Jan 13, 2026 · 80 citations · 66 upvotes · unverified

Read on arXiv

What it shows

The 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.

By Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian and 117 more · arXiv 2601.08584 · PDF

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

More from Mistral AI

All 4
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 →Alignment and safetyUnverifiedFeb 11, 2026Voxtral RealtimeVoxtral Realtime is a streaming speech recognition model trained end-to-end for sub-second latency with performance matching offline systems.Mistral AI10 citations28 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 →

Other reasoning papers

Topic
ReasoningJan 28, 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.Google23.8k citations16 upvotesRead →ReasoningUnverifiedFeb 5, 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsDeepSeekMath 7B improves mathematical reasoning through enhanced data pre-training and Group Relative Policy Optimization, achieving high scores on MATH benchmark without external tools.DeepSeek10.6k citations152 upvotesRead →ReasoningJan 22, 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek5,972 citations458 upvotesRead →ReasoningUnverifiedJun 17, 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-Coder-V2, a Mixture-of-Experts language model, excels in code-specific tasks by enhancing coding and mathematical reasoning capabilities while expanding language support and context length.DeepSeek530 citations73 upvotesRead →ReasoningUnverifiedAug 11, 2025MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.Ai2232 citations45 upvotesRead →ReasoningUnverifiedJul 22, 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.NVIDIA192 citations43 upvotesRead →
About this paper
Venue
arXiv.org
Citations
80, 11 influential · Semantic Scholar
Upvotes
66 · Hugging Face
Lab
Mistral AI · on Companies · on Rounds · on Releases · on Releases

Changes

CitationsNov 2, 2026Influential citations rose from 10 to 11.
CitationsNov 2, 2026Citations rose from 74 to 80.
CitationsOct 12, 2026Citations rose from 69 to 74.
CitationsOct 5, 2026Influential citations rose from 9 to 10.
CitationsOct 5, 2026Citations rose from 64 to 69.
CitationsSep 28, 2026Citations rose from 63 to 64.
CitationsSep 25, 2026A first count of 9 influential citations.
CitationsSep 25, 2026A first count of 63 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.