Papers › SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs

SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs

21 Aug 2024arXiv:2408.11813archive 2025-07-28

Yuanyang Yin, Yaqi Zhao, YaJie Zhang, Ke Lin, Jiahao Wang, Xin Tao, Pengfei Wan, Di Zhang, Baoqun Yin, Wentao Zhang

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities, typically comprising a Vision Encoder, an Adapter, and a Large Language Model (LLM). The adapter serves as the critical bridge between the visual and language components. However, training adapters with image-level supervision often results in significant misalignment, undermining the LLMs' capabilities and limiting the potential of Multimodal LLMs. To address this, we introduce Supervised Embedding Alignment (SEA), a token-level alignment method that leverages vision-language pre-trained models, such as CLIP, to align visual tokens with the LLM's embedding space through contrastive learning. This approach ensures a more coherent integration of visual and language representations, enhancing the performance and interpretability of multimodal LLMs while preserving their inherent capabilities. Extensive experiments show that SEA effectively improves MLLMs, particularly for smaller models, without adding extra data or inference computation. SEA also lays the groundwork for developing more general and adaptable solutions to enhance multimodal systems.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningLanguage ModelingLanguage ModellingLarge Language ModelVisual Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet SEA-PRIME (Vicuna-13B) GPT-4 score 48.8 #71 of 231 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNAdapterCLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections