mlsanityData to 7 Oct 2026

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

arXiv 2603.04800 ↗First posted 5 Mar 2026cs.CVcited by 5

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms. Source code: https://github.com/alibaba/EfficientAI.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 43 of its 44 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

43 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024OmniBench: Towards The Future of Universal Omni-Language Models23 Sep

Other references · 42

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2024Qwen2 Technical Reportcited by 2,076
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  9. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  10. 2019Towards VQA Models That Can Readcited by 1,696
  11. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  12. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
30 more
  1. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  2. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  3. 2025Qwen2.5-Omni Technical Reportcited by 704
  4. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 598
  5. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 466
  6. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 462
  7. 2024SpinQuant: LLM quantization with learned rotationscited by 446
  8. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 403
  9. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 397
  10. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 359
  11. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 320
  12. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 285
  13. 2024SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compressioncited by 231
  14. 2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
  15. 2022Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Modelscited by 176
  16. 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMscited by 165
  17. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 161
  18. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 123
  19. 2024FlatQuant: Flatness Matters for LLM Quantizationcited by 116
  20. 2023ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensationcited by 78
  21. 2024GPTVQ: The Blessing of Dimensionality for LLM Quantizationcited by 78
  22. 2024AffineQuant: Affine Transformation Quantization for Large Language Modelscited by 64
  23. 2025SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compressioncited by 63
  24. 2024MBQ: Modality-Balanced Quantization for Large Vision-Language Modelscited by 45
  25. 2024Low-Rank Quantization-Aware Training for LLMscited by 42
  26. 2025MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantizationcited by 35
  27. 2018A Quantization-Friendly Separable Convolution for MobileNetscited by 22
  28. 2024MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Designcited by 17
  29. 2024Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptationcited by 15
  30. 2024ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantizationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Modelscited by 1
  2. 2026BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answeringcited by 1
  3. 2026Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMscited by 0
  4. 2026OmniKVQuant: KV Cache Quantization for Omni-LLMscited by 0
  5. 2026Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
  2. 2025Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling
  3. 2026Multimodal LLMs under Pairwise Modalities
  4. 2026Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
  5. 2025Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
  6. 2025Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency
  7. 2025Explore How to Inject Beneficial Noise in MLLMs
  8. 2025LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models