mlsanityData to 14 Oct 2026

LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling

arXiv 2506.12826 ↗First posted 15 Jun 2025cs.CVcited by 0

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

Abstract (arXiv)

Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, current pruning methods typically determine optimal strategies through iterative search processes, resulting in substantial computational overhead for on-demand MLLMs adaptation. To address this challenge, we propose LOP, an efficient neural pruning framework that learns optimal pruning strategies from the target pruning constraint, eliminating the need for computationally expensive search-based methods. LOP approach trains autoregressive neural networks (NNs) to directly predict layer-wise pruning strategies adaptive to the target pruning constraint, eliminating the time-consuming iterative searches. Experimental results across multiple tasks show that LOP outperforms state-of-the-art pruning methods in various metrics while achieving up to three orders of magnitude speedup.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 31 of its 34 references that are in the map. First posted on arXiv 15 Jun 2025.

Builds on

31 of 34 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See8 Oct
  2. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference6 Oct
  3. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models11 Mar
  4. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices28 Dec

Other references · 27

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2015VQA: Visual Question Answeringcited by 2,506
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  8. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  9. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  10. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  11. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  12. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
15 more
  1. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  2. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 733
  3. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  4. 2020TextCaps: a Dataset for Image Captioning with Reading Comprehensioncited by 400
  5. 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 385
  6. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 300
  7. 2024TinyLLaVA: A Framework of Small-scale Large Multimodal Modelscited by 164
  8. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 129
  9. 2023Fluctuation-based Adaptive Structured Pruning for Large Language Modelscited by 111
  10. 2024Efficient Multimodal Large Language Models: A Surveycited by 96
  11. 2024ViTamin: Designing Scalable Vision Models in the Vision-Language Eracited by 39
  12. 2024Streamlining Redundant Layers to Compress Large Language Modelscited by 35
  13. 2024Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Modelscited by 24
  14. 2025T'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimizationcited by 4
  15. 2024Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layerscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
  2. 2023Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models
  3. 2026Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
  4. 2025SPAP: Structured Pruning via Alternating Optimization and Penalty Methods
  5. 2024Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
  6. 2025Towards Efficient Automatic Self-Pruning of Large Language Models
  7. 2024NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models
  8. 2025Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study