mlsanityData to 7 Oct 2026

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

arXiv 2502.14786 ↗First posted 20 Feb 2025cs.CV cs.AIcited by 1,127

Not on the map. Why?

Cited by 329 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce SigLIP 2, a family of new multilingual vision-language encoders that build on the success of the original SigLIP. In this second iteration, we extend the original image-text training objective with several prior, independently developed techniques into a unified recipe -- this includes captioning-based pretraining, self-supervised losses (self-distillation, masked prediction) and online data curation. With these changes, SigLIP 2 models outperform their SigLIP counterparts at all model scales in core capabilities, including zero-shot classification, image-text retrieval, and transfer performance when extracting visual representations for Vision-Language Models (VLMs). Furthermore, the new training recipe leads to significant improvements on localization and dense prediction tasks. We also train variants which support multiple resolutions and preserve the input's native aspect ratio. Finally, we train on a more diverse data-mixture that includes de-biasing techniques, leading to much better multilingual understanding and improved fairness. To allow users to trade off inference cost with performance, we release model checkpoints at four sizes: ViT-B (86M), L (303M), So400m (400M), and g (1B).

Key facts. Cited by 1,127 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 367; 2026: 760.

1,127 papers.

Sort:

By area:

  1. 2025Qwen3-VL Technical Reportcited by 2,534
  2. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  3. 2025Qwen-Image Technical Reportcited by 973
  4. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  5. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  6. 2025Qwen3-Omni Technical Reportcited by 451
  7. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  8. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  9. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 233
  10. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 225
  11. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 145
  12. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 144
38 more
  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  2. 2025Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tailcited by 136
  3. 2026Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Groundingcited by 132
  4. 2025Cambrian-S: Towards Spatial Supersensing in Videocited by 123
  5. 2025FLARE: Robot Learning with Implicit World Modelingcited by 105
  6. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 105
  7. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  8. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 104
  9. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 80
  10. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 64
  11. 2025UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generationcited by 64
  12. 20253DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understandingcited by 63
  13. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 61
  14. 2025Meta CLIP 2: A Worldwide Scaling Recipecited by 59
  15. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 52
  16. 2025SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretrainingcited by 51
  17. 2025FineVision: Open Data Is All You Needcited by 51
  18. 2025TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generationcited by 50
  19. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  20. 2026Scaling Text-to-Image Diffusion Transformers with Representation Autoencoderscited by 49
  21. 20253D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understandingcited by 47
  22. 2025TLA: Tactile-Language-Action Model for Contact-Rich Manipulationcited by 46
  23. 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuitcited by 45
  24. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45
  25. 2025Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representationscited by 44
  26. 2025DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabulariescited by 42
  27. 2025Boosting Generative Image Modeling via Joint Image-Feature Synthesiscited by 42
  28. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 42
  29. 2025Visual Representation Alignment for Multimodal Large Language Modelscited by 40
  30. 2026Image Generators are Generalist Vision Learnerscited by 40
  31. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 39
  32. 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policiescited by 39
  33. 2025RemoteSAM: Towards Segment Anything for Earth Observationcited by 38
  34. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 38
  35. 2025Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsificationcited by 36
  36. 2025AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Modelscited by 35
  37. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 34
  38. 2025TUNA: Taming Unified Visual Representations for Native Unified Multimodal Modelscited by 34

50 most cited of 1,127 All 1,127 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
  2. 2025uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data
  3. 2023PaLI-3 Vision Language Models: Smaller, Faster, Stronger
  4. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  5. 2023mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs
  6. 2026Language-Conditioned Visual Grounding with CLIP Multilingual
  7. 2025LaVi: Efficient Large Vision-Language Models via Internal Feature Modulation
  8. 2025Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models