mlsanityData to 14 Oct 2026

INTERLACE: Interleaved Layer Pruning and Efficient Adaptation in Large Vision-Language Models

arXiv 2511.19676 ↗First posted 24 Nov 2025cs.CVcited by 0

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

Abstract (arXiv)

We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lead to significant performance drop when applied to VLMs. Instead, we analyze triplets of consecutive layers to identify local redundancy, removing the most redundant of the first two layers, finetune the remaining layer to compensate for the lost capacity, and freeze the third layer to serve as a stable anchor during finetuning. We found that this interleaved finetune-freeze design enables rapid convergence with minimal data after pruning. By finetuning only a subset of layers on just 1% of the FineVision dataset for one epoch, Interlace achieves 88.9% average performance retention after dropping 25% of the network, achieving SOTA performance. Our code is available at: https://github.com/pmadinei/Interlace.git

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 39 of its 40 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

39 of 40 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM7 Oct
  2. 2025CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models24 Aug
  3. 2025Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers31 Jul
  4. 2025Compression Strategies for Efficient Multimodal LLMs in Medical Contexts29 Jul
  5. 2024Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification1 Dec
  6. 2024ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models30 Nov
  7. 2024PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction22 Oct
  8. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models22 Mar
  9. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models11 Mar
  10. 2023ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models4 Oct

Other references · 29

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  3. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  5. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  6. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  7. 2019Towards VQA Models That Can Readcited by 1,718
  8. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  9. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  10. 2016A Diagram Is Worth A Dozen Imagescited by 804
  11. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 800
  12. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
17 more
  1. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  2. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 455
  3. 2019Reducing Transformer Depth on Demand with Structured Dropoutcited by 439
  4. 2023Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningcited by 415
  5. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 383
  6. 2024LayerSkip: Enabling Early Exit Inference and Self-Speculative Decodingcited by 307
  7. 2024MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?cited by 292
  8. 2023A Survey on Model Compression for Large Language Modelscited by 269
  9. 2024Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Modelscited by 161
  10. 2024SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blockscited by 97
  11. 2025V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoningcited by 68
  12. 2024MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMscited by 62
  13. 2025FineVision: Open Data Is All You Needcited by 53
  14. 2024Streamlining Redundant Layers to Compress Large Language Modelscited by 35
  15. 2024Pruning Foundation Models for High Accuracy without Retrainingcited by 20
  16. 2023Magnitude Attention-based Dynamic Pruningcited by 5
  17. 2025Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration
  2. 2022EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
  3. 2024FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
  4. 2026Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency
  5. 2026Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
  6. 2026Topology-Aware Layer Pruning for Large Vision-Language Models
  7. 2024MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
  8. 2026SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models