Wings: Learning Multimodal LLMs without Text-only Forgetting

• URL: http://arxiv.org/abs/2406.03496v1
• Date: Wed, 5 Jun 2024 17:59:40 GMT
• Title: Wings: Learning Multimodal LLMs without Text-only Forgetting
• Authors: Yi-Kai Zhang, Shiyin Lu, Yang Li, Yanqing Ma, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, De-Chuan Zhan, Han-Jia Ye,
• Abstract summary: Wings is a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks.
• Score: 63.56085426442873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include images and can be addressed within the initial LLM. In this paper, we present Wings, a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Analyzing MLLM attention in multimodal instructions reveals that text-only forgetting is related to the attention shifts from pre-image to post-image text. From that, we construct extra modules that act as the boosted learner to compensate for the attention shift. The complementary visual and textual learners, like "wings" on either side, are connected in parallel within each layer's attention block. Initially, image and text inputs are aligned with visual learners operating alongside the main attention, balancing focus on visual elements. Textual learners are later collaboratively integrated with attention-based routing to blend the outputs of the visual and textual learners. We design the Low-Rank Residual Attention (LoRRA) to guarantee high efficiency for learners. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks. On a newly constructed Interleaved Image-Text (IIT) benchmark, Wings exhibits superior performance from text-only-rich to multimodal-rich question-answering tasks.

Related papers

• Attention Prompting on Image for Large Vision-Language Models [63.794304207664176]
  We propose a new prompting technique named Attention Prompting on Image. We generate an attention heatmap for the input image dependent on the text query with an auxiliary model like CLIP. Experiments on various vison-language benchmarks verify the effectiveness of our technique.
  arXiv  Detail & Related papers  (2024-09-25T17:59:13Z)
• Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs [14.381188702947949]
  Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. This imbalance in LVLMs may result in the instances of hallucinatory. We introduce a training-free algorithm to find an equilibrium point between image comprehension and language inference.
  arXiv  Detail & Related papers  (2024-07-31T17:46:57Z)
• MATE: Meet At The Embedding -- Connecting Images with Long Texts [37.27283238166393]
  Meet At The Embedding (MATE) is a novel approach that combines the capabilities of Large Language Models (LLMs) with Vision Language Models (VLMs) We replace the text encoder of the VLM with a pretrained LLM-based encoder that excels in understanding long texts. We propose two new cross-modal retrieval benchmarks to assess the task of connecting images with long texts.
  arXiv  Detail & Related papers  (2024-06-26T14:10:00Z)
• AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning [15.770849688170477]
  In-context learning (ICL) facilitates Large Language Models exhibiting emergent ability on downstream tasks without updating billions of parameters. Most primary MLLMs are only trained on single-image datasets, making them unable to read multi-modal demonstrations. We propose a general and light-weighted framework textbfAIM to tackle the mentioned problems through textbfAggregating textbfImage information of textbfMultimodal demonstrations to the dense latent space of the corresponding linguistic part.
  arXiv  Detail & Related papers  (2024-06-11T08:12:43Z)
• InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model [108.42241250772643]
  We introduce InternLM-XComposer2, a vision-language model excelling in free-form text-image composition and comprehension. This model goes beyond conventional vision-language understanding, adeptly crafting interleaved text-image content from diverse inputs. Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content.
  arXiv  Detail & Related papers  (2024-01-29T18:59:02Z)
• MLLMs-Augmented Visual-Language Representation Learning [70.5293060238008]
  We demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. We propose "text shearing" to maintain the quality and availability of extended captions.
  arXiv  Detail & Related papers  (2023-11-30T18:05:52Z)
• BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs [101.50522135049198]
  BuboGPT is a multi-modal LLM with visual grounding that can perform cross-modal interaction between vision, audio and language. Our contributions are two-fold: 1) An off-the-shelf visual grounding module based on SAM that extracts entities in a sentence and find corresponding masks in the image. Our experiments show that BuboGPT achieves impressive multi-modality understanding and visual grounding abilities during the interaction with human.
  arXiv  Detail & Related papers  (2023-07-17T15:51:47Z)
• LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation [51.08810811457617]
  vision-language alignment in LLMs is actively being researched to enable multimodal reasoning and visual IO. We develop a method for instruction-tuning an LLM only on text to gain vision-language capabilities for medical images. Our model, LLM-CXR, trained in this approach shows better image-text alignment in both CXR understanding and generation tasks.
  arXiv  Detail & Related papers  (2023-05-19T07:44:39Z)

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.