mlsanityData to 14 Oct 2026

Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI

arXiv 2502.17092 ↗First posted 24 Feb 2025cs.CV cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

We introduce Shakti VLM, a family of vision-language models in the capacity of 1B and 4B parameters designed to address data efficiency challenges in multimodal learning. While recent VLMs achieve strong performance through extensive training data, Shakti models leverage architectural innovations to attain competitive results with fewer tokens. Key advancements include QK-Normalization for attention stability, hybrid normalization techniques, and enhanced positional encoding. A three-stage training strategy further optimizes learning efficiency. Evaluations show that Shakti-Shakti-VLM-1B and Shakti-VLM-4B excel in document understanding, Visual Reasoning, OCR extraction, and general multimodal reasoning. Our results highlight that high performance can be achieved through model design and training strategy rather than sheer data volume, making Shakti an efficient solution for enterprise-scale multimodal tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 15 of its 27 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

15 of 27 references.

References · 15

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  4. 2020GLU Variants Improve Transformercited by 1,804
  5. 2019Root Mean Square Layer Normalizationcited by 1,480
  6. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  7. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
  8. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  9. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  10. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  11. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 483
  12. 2020TextCaps: a Dataset for Image Captioning with Reading Comprehensioncited by 400
3 more
  1. 2022The Stack: 3 TB of permissively licensed source codecited by 359
  2. 2015Visual7W: Grounded Question Answering in Imagescited by 318
  3. 2020Query-Key Normalization for Transformerscited by 280

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
  2. 2025Small Vision-Language Models: A Survey on Compact Architectures and Techniques
  3. 2024A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks
  4. 2025A Survey on Efficient Vision-Language Models
  5. 2022Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
  6. 2025A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
  7. 2026Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies
  8. 2024NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision