Topology-Aware Layer Pruning for Large Vision-Language Models

• URL: http://arxiv.org/abs/2604.16502v1
• Date: Tue, 14 Apr 2026 14:36:53 GMT
• Title: Topology-Aware Layer Pruning for Large Vision-Language Models
• Abstract summary: Large Vision-Language Models (LVLMs) incur substantial computational and memory costs.<n>Existing layer pruning methods typically rely on local similarity metrics or static proxy signals.<n>We propose a topology-aware layer pruning framework for LVLMs.
• Score: 21.06771347736129
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable them to process multimodal information. Despite these advances, Large Vision-Language Models (LVLMs) incur substantial computational and memory costs, hindering deployment in resource-constrained scenarios. Existing layer pruning methods typically rely on local similarity metrics or static proxy signals, failing to capture the global and dynamic evolution of representations across model depth, which often leads to the removal of transition-critical layers. To address this limitation, we propose a topology-aware layer pruning framework for LVLMs. Specifically, we represent layer wise hidden states as point clouds and models their evolution using \textit{simplicial complexes}. By leveraging \textit{zigzag persistent homology}, we quantify inter-layer topological consistency and enable adaptive pruning that preserves critical representational transitions. Extensive experiments on diverse multimodal benchmarks demonstrate that the proposed framework consistently outperforms existing pruning methods across a wide range of sparsity ratios. Our code is available at https://github.com/zpc456/TopoVLM.

Related papers

• IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation [12.812732809987436]
  IMFuse is an instance-aware multi-layer fusion strategy for sequential recommendation.<n>It aggregates multi-layer semantic information by learning global dimension-wise layer preferences.<n>It consistently outperforms state-of-the-art baselines with an average relative improvement of 6.72%.
  arXiv  Detail & Related papers  (2026-07-29T14:58:36Z)
• Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models [73.89069781682032]
  We quantify modality preference of Native Omni-modal Large Language Models (OLLMs)<n>Unlike the text-dominance'' of traditional VLMs, most OLLMs exhibit a pronounced visual preference.<n>Our work provides both a mechanistic understanding and a practical tool for building more trustworthy OLLMs.
  arXiv  Detail & Related papers  (2026-04-18T08:25:52Z)
• ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model [53.15040805435013]
  Vision-language models (VLMs) provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames.<n>We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance.
  arXiv  Detail & Related papers  (2026-03-23T17:59:42Z)
• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• Stateful Cross-layer Vision Modulation [19.730096071316876]
  multimodal large language models (MLLMs) widely adopt multi-layer visual feature fusion to enhance visual representation.<n>Existing approaches typically perform static concatenation or weighted aggregation after visual encoding, without intervening in the representation formation process itself.<n>We propose a cross-layer memory-modulated vision framework(SCVM) to address these limitations.
  arXiv  Detail & Related papers  (2026-02-28T13:57:19Z)
• Multimodal Latent Reasoning via Hierarchical Visual Cues Injection [16.779425236020433]
  This work posits that robust reasoning should evolve within a latent space, integrating multimodal signals seamlessly.<n>We propose a novel framework that instills deliberate, "slow thinking" without depending on superficial textual rationales.<n>We show that test-time scaling is effective when incorporating vision knowledge, and that integrating hierarchical information significantly enhances the model's understanding of complex scenes.
  arXiv  Detail & Related papers  (2026-02-05T06:31:12Z)
• PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs [59.78917775399492]
  Multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability.<n>We propose a training-free framework to mitigate this degradation.
  arXiv  Detail & Related papers  (2026-01-12T15:27:51Z)
• ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction [55.21514454560188]
  Unified multimodal models significantly improve visual generation by combining vision-grained models (VLMs) with diffusion models.<n>Existing methods struggle to fully balance sufficient interaction and flexible implementation due to vast representation difference.<n>We propose textbfParaUni, which extracts features from variants VLM's layers in a textbfParallel way for comprehensive information interaction.
  arXiv  Detail & Related papers  (2025-12-05T04:41:57Z)
• RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging [33.22889542330089]
  Internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge.<n>We propose RECALL, a representation-aware model merging framework for continual learning without access to historical data.
  arXiv  Detail & Related papers  (2025-10-23T12:17:37Z)
• Layer by Layer: Uncovering Hidden Representations in Language Models [28.304269706993942]
  We show that intermediate layers can encode even richer representations, often improving performance on a range of downstream tasks.<n>Our framework highlights how each layer balances information compression and signal preservation, revealing why mid-depth embeddings can exceed the last layer's performance.
  arXiv  Detail & Related papers  (2025-02-04T05:03:42Z)
• GrootVL: Tree Topology is All You Need in State Space Model [66.36757400689281]
  GrootVL is a versatile multimodal framework that can be applied to both visual and textual tasks. Our method significantly outperforms existing structured state space models on image classification, object detection and segmentation. By fine-tuning large language models, our approach achieves consistent improvements in multiple textual tasks at minor training cost.
  arXiv  Detail & Related papers  (2024-06-04T15:09:29Z)
• Probing Multimodal Large Language Models for Global and Local Semantic Representations [57.25949445963422]
  We study which layers of Multimodal Large Language Models make the most effort to the global image information. In this study, we find that the intermediate layers of models can encode more global semantic information. We find that the topmost layers may excessively focus on local information, leading to a diminished ability to encode global information.
  arXiv  Detail & Related papers  (2024-02-27T08:27:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.