Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

• URL: http://arxiv.org/abs/2503.02597v1
• Date: Tue, 04 Mar 2025 13:18:33 GMT
• Title: Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
• Authors: Wei-Yao Wang, Zhao Wang, Helen Suzuki, Yoshiyuki Kobayashi,
• Abstract summary: We present AKI, a novel MLLM that unlocks causal attention into modality-mutual attention (MMA) to enable image tokens to attend to text tokens.<n>Our MMA design is intended to be generic, allowing for application across various modalities, and scalable to accommodate diverse multimodal scenarios.
• Score: 7.03771340666549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in MLLMs has emerged as a critical challenge, where the textual responses generated by these models are not factually aligned with the given text-image inputs. Existing efforts to address vision-language misalignment have focused on developing specialized vision-language connectors or leveraging visual instruction tuning from diverse domains. In this paper, we tackle this issue from a fundamental yet unexplored perspective by revisiting the core architecture of MLLMs. Most MLLMs are typically built on decoder-only LLMs consisting of a causal attention mechanism, which limits the ability of earlier modalities (e.g., images) to incorporate information from later modalities (e.g., text). To address this problem, we propose AKI, a novel MLLM that unlocks causal attention into modality-mutual attention (MMA) to enable image tokens to attend to text tokens. This simple yet effective design allows AKI to achieve superior performance in 12 multimodal understanding benchmarks (+7.2% on average) without introducing additional parameters and increasing training time. Our MMA design is intended to be generic, allowing for application across various modalities, and scalable to accommodate diverse multimodal scenarios. The code is publicly available at https://github.com/sony/aki, and we will release our AKI-4B model to encourage further advancements in MLLMs across various directions.

Related papers

• Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model [63.14883657299359]
  Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. tuning MLLMs for downstream tasks encounters two key challenges: Task-Expert, where distribution shifts between pre-training and target datasets constrain target performance, and OpenWorld Stabilization, where catastrophic forgetting erases the model general knowledge.
  arXiv  Detail & Related papers  (2025-03-06T15:29:13Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE) DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy [37.471419716572086]
  There is a significant gap in instruction-following capabilities between Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) We propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap.
  arXiv  Detail & Related papers  (2024-11-23T05:03:32Z)
• MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs [61.56904387052982]
  This paper proposes a new visual grounding task called multi-context visual grounding. It aims to localize instances of interest across multiple images based on open-ended text prompts. We benchmark over 20 state-of-the-art MLLMs and foundation models with potential multi-context visual grounding capabilities.
  arXiv  Detail & Related papers  (2024-10-16T07:52:57Z)
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders [89.41055673919895]
  This study explores the design space for MLLMs using a mixture of vision encoders and resolutions.<n>We discover that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies.<n>The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.
  arXiv  Detail & Related papers  (2024-08-28T17:59:31Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• 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)
• NoteLLM-2: Multimodal Large Representation Models for Recommendation [71.87790090964734]
  Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks.<n>Their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains underexplored.<n>We propose an end-to-end fine-tuning method that customizes the integration of any existing LLMs and vision encoders for efficient multimodal representation.
  arXiv  Detail & Related papers  (2024-05-27T03:24:01Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics [32.123919380959485]
  Multi-modal large language models (MLLMs) are trained based on large language models (LLM) While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. We show that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical alignment.
  arXiv  Detail & Related papers  (2023-09-13T17:57:21Z)
• A Survey on Multimodal Large Language Models [71.63375558033364]
  Multimodal Large Language Model (MLLM) represented by GPT-4V has been a new rising research hotspot.<n>This paper aims to trace and summarize the recent progress of MLLMs.
  arXiv  Detail & Related papers  (2023-06-23T15:21:52Z)

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.