Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, and has a strong compatibility in transformation architecture. MoLE incorporates sparsely gated experts into LLMs to achieve painless improvements with roughly unchanged inference costs. In response to task interference, our MoME specializes in both vision and language modality to adapt to task discrepancies. Extensive experiments show that MoME significantly improves the performance of generalist MLLMs across various VL tasks.

Vision-language (VL) pre-training has recently received considerable attention.

Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model by inserting cross-attention into the image and text backbones to better capture multimodal interactions. In addition, unlike previous work that is either only pre-trained on image-text data or on fine-grained data with box-level annotations, we present a two-stage pre-training strategy that uses both these kinds of data efficiently: (i) coarse-grained pre-training based on image-text data; followed by (ii) fine-grained pre-training based on image-text-box data. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection. Using deep multimodal fusion coupled with the two-stage pre-training, FIBER provides consistent performance improvements over strong baselines across all tasks, often outperforming methods using magnitudes more data. Code is released at https://github.com/microsoft/FIBER.

Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, and has a strong compatibility in transformation architecture.

Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model by inserting cross-attention into the image and text backbones to better capture multimodal interactions. In addition, unlike previous work that is either only pre-trained on image-text data or on fine-grained data with box-level annotations, we present a two-stage pre-training strategy that uses both these kinds of data efficiently: (i) coarse-grained pre-training based on image-text data; followed by (ii) fine-grained pre-training based on image-text-box data.

Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often significantly decreases performance on natural language understanding and generation tasks, compared to the original LLM. This study investigates this issue using the LLaVA MLLM, treating the integration as a continual learning problem. We evaluate five continual learning methods to mitigate forgetting and identify a technique that enhances visual understanding while minimizing linguistic performance loss. Our approach reduces linguistic performance degradation by up to 15% over the LLaVA recipe, while maintaining high multimodal accuracy. We also demonstrate the robustness of our method through continual learning on a sequence of vision-language tasks, effectively preserving linguistic skills while acquiring new multimodal capabilities. Figure 1: Summary results of the best CL methods we evaluated for training LLaVA 1.5 compared to the unimodal base LLM and the original version of LLaVA 1.5. All results are with Pythia 2.8B as the base LLM. The best method has almost the same vision-language (VL) accuracy while providing a large increase in linguistic performance on 1 NLG and 4 NLU tasks by 8% and 2% (absolute), resp.

Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still preliminary because existing datasets do not permit a comprehensive evaluation of the fine-grained visual linguistic abilities of VLMs across multiple languages. To further explore the strengths of VLMs, such as GPT-4V \cite{openai2023GPT4}, we developed new datasets for the systematic and qualitative analysis of VLMs. Our contribution is four-fold: 1) we introduced nine vision-and-language (VL) tasks (including object recognition, image-text matching, and more) and constructed multilingual visual-text datasets in four languages: English, Japanese, Swahili, and Urdu through utilizing templates containing \textit{questions} and prompting GPT4-V to generate the \textit{answers} and the \textit{rationales}, 2) introduced a new VL task named \textit{unrelatedness}, 3) introduced rationales to enable human understanding of the VLM reasoning process, and 4) employed human evaluation to measure the suitability of proposed datasets for VL tasks. We show that VLMs can be fine-tuned on our datasets. Our work is the first to conduct such analyses in Swahili and Urdu. Also, it introduces \textit{rationales} in VL analysis, which played a vital role in the evaluation.

With the success of self-supervised learning, multimodal foundation models have rapidly adapted a wide range of downstream tasks driven by vision and language (VL) pretraining. State-of-the-art methods achieve impressive performance by pre-training on large-scale datasets. However, bridging the semantic gap between the two modalities remains a nonnegligible challenge for VL tasks. In this work, we propose an efficient computation framework for multimodal alignment by introducing a novel visual semantic module to further improve the performance of the VL tasks. Specifically, we propose a flexible model, namely Artificial-Spiking Hierarchical Networks (ASH-Nets), which combines the complementary advantages of Artificial neural networks (ANNs) and Spiking neural networks (SNNs) to enrich visual semantic representations. In particular, a visual concrete encoder and a semantic abstract encoder are constructed to learn continuous and discrete latent variables to enhance the flexibility of semantic encoding. Considering the spatio-temporal properties of SNNs modeling, we introduce a contrastive learning method to optimize the inputs of similar samples. This can improve the computational efficiency of the hierarchical network, while the augmentation of hard samples is beneficial to the learning of visual representations. Furthermore, the Spiking to Text Uni-Alignment Learning (STUA) pre-training method is proposed, which only relies on text features to enhance the encoding ability of abstract semantics. We validate the performance on multiple well-established downstream VL tasks. Experiments show that the proposed ASH-Nets achieve competitive results.

Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models do not possess the ability to conduct in-context learning. How can we enable in-context learning for VL models? In this paper, we study an interesting hypothesis: can we transfer the in-context learning ability from the language domain to VL domain? Specifically, we first meta-trains a language model to perform in-context learning on NLP tasks (as in MetaICL); then we transfer this model to perform VL tasks by attaching a visual encoder. Our experiments suggest that indeed in-context learning ability can be transferred cross modalities: our model considerably improves the in-context learning capability on VL tasks and can even compensate for the size of the model significantly. On VQA, OK-VQA, and GQA, our method could outperform the baseline model while having 20 times fewer parameters.