MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches focus on single-modality adjustments, leading to suboptimal alignment and limited generalization. |
| Approach: | They propose a plug-and-play framework for visual recognition that integrates a Harmonic Cross-Modal Adapter and a Meta-Template Optimization module. |
| Outcome: | Extensive experiments across multiple fine-grained visual recognition benchmarks show that MAFMO consistently improves existing methods’ performance on both novel classes and harmonic mean while maintaining robustness under various challenging conditions with minimal computational overhead. |
Similar Papers
Advancing Vision-Language Models with Adapter Ensemble Strategies (2024.findings-emnlp)
Copied to clipboard
| Challenge: | CLIP revolutes vision-language pretraining by using contrastive learning on paired web data. |
| Approach: | They propose to combine a "adapter ensemble" with traditional machine learning techniques to augment large-scale pretrained vision-language models. |
| Outcome: | The proposed model outperforms baselines and derives improvement when the number of ensemble parameters increases. |
Two Challenges, One Solution: Robust Multimodal Learning through Dynamic Modality Recognition and Enhancement (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods require full-modality data during training phase or require explicit annotations to detect missing modalities. |
| Approach: | They propose a Dynamic modality Recognition and Enhancement for Adaptive Multimodal fusion framework that directs selective reconstruction of missing or underperforming modalities. |
| Outcome: | The proposed framework outperforms several baseline and state-of-the-art models on three benchmark datasets. |
Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to merge multi-modal knowledge only use one fusion strategy . however, the impact of the fusion on individual entities could be ignored . |
| Approach: | They propose an adaptive multi-modal feature fusion strategy for entity alignment that selects the optimal entity-level feature blending strategy. |
| Outcome: | The proposed model achieves state-of-the-art (SOTA) performance compared to models using the same modality on a dataset with multiple inconsistent images and styles. |
Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows that vision-language models have modality gaps that persist even in well-aligned models. |
| Approach: | They propose a modality-dominance score to measure and leverage modality gaps . they propose automatic interpretability metrics to evaluate these features in a scalable manner . |
| Outcome: | The proposed framework allows for training-free probing and editing methods for understanding model perception across genders and generating adversarial examples. |
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)
Copied to clipboard
Yixia Li, Yaqing Shi, Zhiwen Ruan, Dongdong Zhang, Lingjie Jiang, Shaohan Huang, Yun Chen, Guanhua Chen, Furu Wei
| Challenge: | Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision. |
| Approach: | They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone. |
| Outcome: | The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data. |
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing fine-tuning approaches for compositional understanding compromise performance in zero-shot multi-modal tasks. |
| Approach: | They propose a method to enhance compositional understanding in pre-trained vision and language models without sacrificing performance in zero-shot multi-modal tasks. |
| Outcome: | The proposed method achieves compositionality on par with state-of-the-art models and retains strong multi-modal capabilities. |
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)
Copied to clipboard
Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si
| Challenge: | Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. |
| Approach: | They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. |
| Outcome: | The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. |
MoExtend: Tuning New Experts for Modality and Task Extension (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing instruction tuning methods for large language models (LLMs) are costly and difficult to implement. |
| Approach: | They propose a framework to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. |
| Outcome: | The proposed framework enables rapid adaptation and extension to new modal data or tasks without tuning pretrained models. |
Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. |
| Approach: | They propose a diagnostic method based on cross-modal input ablation to assess the extent to which pretrained models integrate cross-module information. |
| Outcome: | The proposed method evaluates the model's performance on the other modality based on inputs from one or both modality. |
Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (2026.acl-long)
Copied to clipboard
| Challenge: | a contrastive learning approach for vision-language models is needed to capture compositional information. |
| Approach: | They propose a framework that masks compositional concepts in one modality and reconstructs them conditioned on full contextual information from the other . |
| Outcome: | The proposed framework enhances compositionality in visual language models and improves their ability to capture syntactic structure and linguistic information. |