mlsanityData to 7 Oct 2026

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One

arXiv 2312.06709 ↗First posted 10 Dec 2023cs.CVcited by 165

Not on the map. Why?

Cited by 23 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. In pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework. Code: https://github.com/NVlabs/RADIO

Key facts. Cited by 165 papers in the map (data through 7 Oct 2026). Builds on 47 of its 66 references that are in the map. First posted on arXiv 10 Dec 2023.

Builds on

47 of 66 references.

References · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  7. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  8. 2015Fast R-CNNcited by 2,930
  9. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  10. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  11. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  12. 2019Towards VQA Models That Can Readcited by 1,696
35 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  2. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  3. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  4. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  5. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  6. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  7. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  8. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  9. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  10. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  11. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  12. 2013Do Deep Nets Really Need to be Deep?cited by 466
  13. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  14. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  15. 2019Variational Information Distillation for Knowledge Transfercited by 321
  16. 2018Paraphrasing Complex Network: Network Compression via Factor Transfercited by 255
  17. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  18. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  19. 2018Knowledge Distillation by On-the-Fly Native Ensemblecited by 186
  20. 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapsecited by 154
  21. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  22. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  23. 2022Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillationcited by 93
  24. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  25. 2019GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answeringcited by 77
  26. 2021Adaptive Multi-Teacher Multi-level Knowledge Distillationcited by 69
  27. 2020Reinforced Multi-Teacher Selection for Knowledge Distillationcited by 62
  28. 2019Ensemble Knowledge Distillation for Learning Improved and Efficient Networkscited by 46
  29. 2019Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering Systemcited by 43
  30. 2022EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Predictioncited by 42
  31. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  32. 2019EvalAI: Towards Better Evaluation Systems for AI Agentscited by 34
  33. 2019Highlight Every Step: Knowledge Distillation via Collaborative Teachingcited by 20
  34. 2023Window Attention is Bugged: How not to Interpolate Position Embeddingscited by 18
  35. 2023Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networkscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 20; 2025: 85; 2026: 60.

165 papers.

Sort:

By area:

  1. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  3. 2024Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolutioncited by 157
  4. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  5. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 104
  6. 2024RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Modelscited by 88
  7. 2025Ola: Pushing the Frontiers of Omni-Modal Language Modelcited by 79
  8. 2024Theia: Distilling Diverse Vision Foundation Models for Robot Learningcited by 56
  9. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 48
  10. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 42
  11. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 40
  12. 2025Visual Representation Alignment for Multimodal Large Language Modelscited by 40
38 more
  1. 2024Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Renderingcited by 35
  2. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 34
  3. 2025DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perceptioncited by 33
  4. 2025SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillationcited by 29
  5. 2024SPA: 3D Spatial-Awareness Enables Effective Embodied Representationcited by 28
  6. 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teacherscited by 28
  7. 2024Feat2GS: Probing Visual Foundation Models with Gaussian Splattingcited by 26
  8. 2025Scaling Vision Pre-Training to 4K Resolutioncited by 26
  9. 2025AnyUp: Universal Feature Upsamplingcited by 26
  10. 2025MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoderscited by 25
  11. 2025Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Modelcited by 24
  12. 2025RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Explorationcited by 23
  13. 2025LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Modelscited by 23
  14. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  15. 2025Comprehensive language-image pre-training for 3D medical image understandingcited by 20
  16. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
  17. 2024Revisit Anything: Visual Place Recognition via Image Segment Retrievalcited by 19
  18. 2024Active Data Curation Effectively Distills Large-Scale Multimodal Modelscited by 19
  19. 2025Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assetscited by 19
  20. 2024PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillationcited by 17
  21. 2024ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentationcited by 16
  22. 2025Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMscited by 16
  23. 2025SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inferencecited by 15
  24. 2024Brain Mapping with Dense Features: Grounding Cortical Semantic Selectivity in Natural Images With Vision Transformerscited by 13
  25. 2025Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understandingcited by 13
  26. 2024UNIT: Unifying Image and Text Recognition in One Vision Encodercited by 12
  27. 2025Vision Transformers with Self-Distilled Registerscited by 12
  28. 2025Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Modelscited by 12
  29. 2026INSID3: Training-Free In-Context Segmentation with DINOv3cited by 12
  30. 2025Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teacherscited by 11
  31. 2025Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Videocited by 10
  32. 2026C-RADIOv4 (Tech Report)cited by 10
  33. 2026Representation Distribution Matching for One-Step Visual Generationcited by 10
  34. 2024Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillationcited by 9
  35. 2025'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documentscited by 9
  36. 2025CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidancecited by 9
  37. 2025Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perceptioncited by 9
  38. 2025UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encodingcited by 9

50 most cited of 165 All 165 (JSON)