MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs

arXiv:2610.01434 · cs.CV, cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/EIT-NLP/MWOP

Terminology

• Pruning — 115× in this paper · explained in 4 episodes
• Grounding — 53× in this paper · explained in 3 episodes
• Benchmark — 42× in this paper · explained in 2 episodes
• Redundancy — 34× in this paper · explained in 2 episodes
• Calibration — 13× in this paper · explained in 7 episodes
• Conference on Computer Vision and Pattern Recognition — 7× in this paper
• Generalization — 4× in this paper · explained in 13 episodes
• Sparsity — 4× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Modality-aware Width-wise Operation Pruning — 3× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Guided attention — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• International Conference on Computer Vision — 1× in this paper
• Joint Attention — 1× in this paper · explained in 2 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Token Merging: Your ViT But Faster
• Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy
• MANTIS: Interleaved Multi-Image Instruction Tuning
• LLaVA-OneVision: Easy Visual Task Transfer
• Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs
• ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
• UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
• PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
• LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
• Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models