mlsanityData to 14 Oct 2026

Compression Strategies for Efficient Multimodal LLMs in Medical Contexts

arXiv 2507.21976 ↗First posted 29 Jul 2025cs.AIcited by 1

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

Abstract (arXiv)

Multimodal Large Language Models (MLLMs) hold huge potential for usage in the medical domain, but their computational costs necessitate efficient compression techniques. This paper evaluates the impact of structural pruning and activation-aware quantization on a fine-tuned LLAVA model for medical applications. We propose a novel layer selection method for pruning, analyze different quantization techniques, and assess the performance trade-offs in a prune-SFT-quantize pipeline. Our proposed method enables MLLMs with 7B parameters to run within 4 GB of VRAM, reducing memory usage by 70% while achieving 4% higher model performance compared to traditional pruning and quantization techniques in the same compression ratio.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 11 of its 17 references that are in the map. First posted on arXiv 29 Jul 2025.

Builds on

11 of 17 references.

References · 11

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  7. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  8. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 383
  9. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  10. 2023Multimodal Large Language Models: A Surveycited by 195
  11. 2024Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methodscited by 82

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs
  2. 2025When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models
  3. 2024Aggressive Post-Training Compression on Extremely Large Language Models
  4. 2024LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
  5. 2025Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation
  6. 2025LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models
  7. 2025Semantic Retention and Extreme Compression in LLMs: Can We Have Both?
  8. 2023Compressing LLMs: The Truth is Rarely Pure and Never Simple