Modeling Cross-vision Synergy for Unified Large Vision Model

• URL: http://arxiv.org/abs/2603.03564v1
• Date: Tue, 03 Mar 2026 22:44:43 GMT
• Title: Modeling Cross-vision Synergy for Unified Large Vision Model
• Authors: Shengqiong Wu, Lanhu Wu, Mingyang Bao, Wenhao Xu, Hanwang Zhang, Shuicheng Yan, Hao Fei, Tat-Seng Chua,
• Abstract summary: PolyV is a unified large vision model that achieves cross-vision synergy at both the architectural and training levels.<n>PolyV consistently outperforms existing models, achieving over 10% average improvement over its backbone.
• Score: 130.37489011094036
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advances in large vision models (LVMs) have shifted from modality-specific designs toward unified architectures that jointly process images, videos, and 3D data. However, existing unified LVMs primarily pursue functional integration, while overlooking the deeper goal of cross-vision synergy: the ability to reason over complementary priors across visual modalities. To address this, we present PolyV, a unified LVM that achieves cross-vision synergy at both the architectural and training levels. Architecturally, PolyV adopts a sparse Mixture-of-Experts LVM coordinated by a dynamic modality router, allowing each expert to specialize in modality-specific priors while enabling bidirectional interaction and mutual refinement across modalities. Training-wise, a synergy-aware paradigm combines modality-specific pretraining with coarse-to-fine synergy tuning via knowledge distillation and object-/relation-level alignment. Extensive experiments on 10 benchmarks spanning image, video, and 3D understanding, including synergy-focused datasets requiring spatial or temporal priors, demonstrate that PolyV consistently outperforms existing models, achieving over 10% average improvement over its backbone. Overall, PolyV establishes a unified framework for synesthetic visual reasoning, advancing toward truly synergistic LVMs. Project page: https://sqwu.top/PolyV.

Related papers

• Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality [59.651410243721045]
  CoCoA is a Content reconstruction pre-training paradigm based on Collaborative Attention for multimodal embedding optimization.<n>We introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding EOS> embeddings.<n>Experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality.
  arXiv  Detail & Related papers  (2026-03-02T05:34:45Z)
• 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)
• MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm [25.7631608456086]
  MindGPT-4ov is a general post-training paradigm spanning data production, model training, and efficient deployment.<n>It achieves state-of-the-art performance across multiple benchmarks at low cost.<n>MindGPT-4ov also demonstrates superior user experience in vertical domain tasks.
  arXiv  Detail & Related papers  (2025-12-02T16:04:11Z)
• Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models [75.45940282834327]
  We introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs.<n>We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs.<n>Our approach employs a two-stage fine-tuning strategy, resulting in significant improvements across multiple tasks.
  arXiv  Detail & Related papers  (2025-11-03T14:27:00Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey [45.10095869091538]
  Vision-Language-Action (VLA) models, built upon Large Vision-Language Models (VLMs) pretrained on vast image-text datasets, have emerged as a transformative paradigm.<n>This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation.
  arXiv  Detail & Related papers  (2025-08-18T16:45:48Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• UniViTAR: Unified Vision Transformer with Native Resolution [37.63387029787732]
  We introduce UniViTAR, a family of homogeneous vision foundation models tailored for unified visual modality and native resolution scenario.<n>A progressive training paradigm is introduced, which strategically combines two core mechanisms.<n>In parallel, a hybrid training framework further synergizes sigmoid-based contrastive loss with feature distillation from a frozen teacher model.
  arXiv  Detail & Related papers  (2025-04-02T14:59:39Z)
• Astrea: A MOE-based Visual Understanding Model with Progressive Alignment [10.943104653307294]
  Vision-Language Models (VLMs) based on Mixture-of-Experts (MoE) architectures have emerged as a pivotal paradigm in multimodal understanding.<n>We propose Astrea, a novel multi-expert collaborative VLM architecture based on progressive pre-alignment.
  arXiv  Detail & Related papers  (2025-03-12T14:44:52Z)

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.