mlsanityData to 14 Oct 2026

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

arXiv 2604.24954 ↗First posted 27 Apr 2026cs.LG cs.AI cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 27 Apr 2026.

Builds on

32 of 44 references.

References · 32

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  6. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  7. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  8. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  9. 2019Towards VQA Models That Can Readcited by 1,718
  10. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  11. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  12. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
20 more
  1. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  2. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  3. 2016A Diagram Is Worth A Dozen Imagescited by 804
  4. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 567
  5. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  6. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 378
  7. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 239
  8. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMscited by 234
  9. 2025WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMscited by 155
  10. 2023Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognitioncited by 124
  11. 2025Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalitiescited by 110
  12. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 89
  13. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 76
  14. 2025Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and ASTcited by 60
  15. 2025OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLMcited by 59
  16. 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durationscited by 58
  17. 2025OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoningcited by 25
  18. 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluationcited by 23
  19. 2023Updated Corpora and Benchmarks for Long-Form Speech Recognitioncited by 10
  20. 2025Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inferencecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 30.

30 papers.

Sort:

By area:

  1. 2026DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Modelscited by 8
  2. 2026Toward Native Multimodal Modeling: A Roadmapcited by 7
  3. 2026OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidancecited by 4
  4. 2026Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videoscited by 2
  5. 2026Out of Sight, Still in Mind: Token Compression for Omni-LLMscited by 2
  6. 2026OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agentscited by 2
  7. 2026SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Modelscited by 1
  8. 2026NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generationcited by 1
  9. 2026Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interactioncited by 1
  10. 2026Omni2Web: Benchmarking Audiovisual Website Developmentcited by 1
  11. 2026AeroVerse-SatAgent: UAV-Satellite Collaborative Spatial Reasoning Inspired by the Dual Visual Pathway Theory of Cognitive Neurosciencecited by 0
  12. 2026Noisy-Channel Minimum Bayes Risk Decodingcited by 0
18 more
  1. 2026PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languagescited by 0
  2. 2026HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationalescited by 0
  3. 2026Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Controlcited by 0
  4. 2026The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language modelscited by 0
  5. 2026Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiencescited by 0
  6. 2026Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Modelscited by 0
  7. 2026Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agentscited by 0
  8. 2026OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agentscited by 0
  9. 2026MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Modelscited by 0
  10. 2026What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generationcited by 0
  11. 2026Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Modelscited by 0
  12. 2026OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoningcited by 0
  13. 2026OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoningcited by 0
  14. 2026Text-Centric Post-Training for Omni-Modal Reasoningcited by 0
  15. 2026Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoningcited by 0
  16. 2026SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understandingcited by 0
  17. 2026When History Helps and Hurts: Selective History Use across Multimodal Turnscited by 0
  18. 2026OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025NVIDIA Nemotron 3: Efficient and Open Intelligence
  2. 2025Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
  3. 2025NVIDIA Nemotron Nano V2 VL
  4. 2026Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
  5. 2025NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
  6. 2025Qwen3-Omni Technical Report
  7. 2026Qwen3.5-Omni Technical Report
  8. 2026Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning