Hierarchical Pre-Training of Vision Encoders with Large Language Models

• URL: http://arxiv.org/abs/2604.00086v1
• Date: Tue, 31 Mar 2026 18:00:39 GMT
• Title: Hierarchical Pre-Training of Vision Encoders with Large Language Models
• Abstract summary: HIVE (Hierarchical Pre-Training of Visions) is a novel framework that enhances vision-language alignment.<n>Unlike conventional methods that flatten image embeddings, HIVE enables structured feature fusion across multiple layers.<n>Our results highlight the benefits of hierarchical feature integration, paving the way for more efficient vision-language models.
• Score: 4.52797541666943
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The field of computer vision has experienced significant advancements through scalable vision encoders and multimodal pre-training frameworks. However, existing approaches often treat vision encoders and large language models (LLMs) as independent modules, limiting the integration of hierarchical visual features. In this work, we propose HIVE (Hierarchical Pre-Training of Vision Encoders), a novel framework that enhances vision-language alignment by introducing hierarchical cross-attention between the vision encoder and LLM. Unlike conventional methods that flatten image embeddings, HIVE enables structured feature fusion across multiple layers, improving gradient flow and representation learning. To optimize this interaction, we introduce a three-stage training strategy that progressively aligns the vision encoder with the LLM, ensuring stable optimization and effective multimodal fusion. Empirical evaluations demonstrate that HIVE achieves superior performance not only in image classification but also on various vision-language tasks, outperforming self-attention-based methods in benchmarks such as MME, GQA, OK-VQA, and ScienceQA. Our results highlight the benefits of hierarchical feature integration, paving the way for more efficient and expressive vision-language models.

Related papers

• CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning [79.07656918674684]
  CoME-VL is a modular fusion framework that integrates a contrastively trained vision encoder with a self-supervised DINO encoder.<n>Our method achieves state-of-the-art performance on RefCOCO for detection while improving over the baseline by a large margin.
  arXiv  Detail & Related papers  (2026-04-03T17:59:51Z)
• VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization [87.26383908243878]
  We show that vision encoders within Multimodal Large Language Models exhibit deficiencies in their dense feature representations.<n>We propose VersaViT, a well-rounded vision transformer that instantiates a novel multi-task framework for collaborative post-training.
  arXiv  Detail & Related papers  (2026-02-10T16:08:19Z)
• CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models [7.442802086966249]
  Context-Aware Image Representation Prioritization via Ensemble (CARPE) is a model-agnostic framework which introduces vision-integration layers and a context-aware ensemble strategy.<n>CARPE is designed to be effectively integrated with most open-source LVLMs that consist of a vision encoder and a language model.
  arXiv  Detail & Related papers  (2026-01-20T05:44:33Z)
• From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion [91.35078719566472]
  Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection.<n>We introduce Cross-Layer Injection (CLI), a novel and lightweight framework that forges a dynamic many-to-many bridge between the two modalities.
  arXiv  Detail & Related papers  (2026-01-15T18:59:10Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
  X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM. X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders. It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
  arXiv  Detail & Related papers  (2024-07-18T18:39:54Z)

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.