TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in unimodal models, its application to MLLMs often yields limited success. Our analysis discovers that conventional methods fail to account for the unique token attributes across layers and modalities inherent to MLLMs. Inspired by this observation, we propose TAMP, a simple yet effective pruning framework tailored for MLLMs, featuring two key components: (1) Diversity-Aware Sparsity, which adjusts sparsity ratio per layer based on diversities among multimodal output tokens, preserving more parameters in high-diversity layers; and (2) Adaptive Multimodal Input Activation, which identifies representative multimodal input tokens using attention scores to guide unstructured weight pruning. We validate our method on two state-of-the-art MLLMs: LLaVA-NeXT, designed for vision-language tasks, and VideoLLaMA2, capable of processing audio, visual, and language modalities. Empirical experiments across various multimodal evaluation benchmarks demonstrate that each component of our approach substantially outperforms existing pruning techniques.
Code (1)
Tasks
DiversityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Layer-adaptive sparsity for the Magnitude-based Pruning
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without…
image-classificationImage ClassificationNetwork PruningDLP: Dynamic Layerwise Pruning in Large Language Models
Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategie…
parameter-efficient fine-tuningOPTISHEAR: Towards Efficient and Adaptive Pruning of Large Language Models via Evolutionary Optimization
Post-training pruning has emerged as a crucial optimization technique as large language models (LLMs) continue to grow rapidly. However, the significant variations in weight distributions across different LLMs make fixed…
Model CompressionCATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundan…
Domain AdaptationCLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Tra…