VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation

• URL: http://arxiv.org/abs/2605.24675v1
• Date: Sat, 23 May 2026 17:25:45 GMT
• Title: VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation
• Abstract summary: VaaWIT is an end-to-end framework that adapts Large Language Models for multilingual Web image translation.<n>A Dual-Stream Attention Module (DSAM) facilitates bidirectional interaction between multilingual semantic features and detailed visual representations.<n>A Visual-Aware Adapter (VAA) dynamically injects these fused visual cues into the frozen LLM backbone.
• Score: 18.312531006938162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within social media and e-commerce domains. Although Large Vision-Language Models (LVLMs) have advanced multimodal understanding, applying them to Web image translation remains challenging due to the visual representation gap: standard encoders often prioritize high-level semantics over the fine-grained visual details required for recognizing diverse character morphologies. To address this challenge, we propose VaaWIT, an end-to-end framework that adapts Large Language Models for multilingual Web image translation. The framework introduces two key technical contributions: (1) a Dual-Stream Attention Module (DSAM), which facilitates bidirectional interaction between multilingual semantic features and detailed visual representations, thereby synthesizing unified features robust to textual variations; and (2) a Visual-Aware Adapter (VAA), a parameter-efficient fine-tuning strategy that dynamically injects these fused visual cues into the frozen LLM backbone. This design enables the model to align the visual context with linguistic reasoning effectively while minimizing computational costs. Extensive experiments on eight tasks on three public benchmarks demonstrate that VaaWIT significantly outperforms state-of-the-art (SOTA) open-source baselines and achieves competitive performance against proprietary models. These results validate the efficacy of integrating fine-grained visual perception into LLMs for complex Web content analysis.

Related papers

• DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval [8.127699016544822]
  We introduce DREAM: Dual-path Representation Enhancement and Alignment Model.<n>We design a hierarchical vision encoder with cascaded group attention, which integrates spatial and temporal information.<n>We validate DREAM through comprehensive evaluations on the widely-used MSRVTT, MSVD and LSMDC benchmark datasets.
  arXiv  Detail & Related papers  (2026-06-17T13:35:50Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving [61.992824291296444]
  Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs)<n>This paper proposes a paradigm shift: instead of training end-to-end vision-language reasoning models, we advocate for developing a decoupled reasoning framework.
  arXiv  Detail & Related papers  (2025-05-23T08:18:00Z)
• Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains [31.828341309787042]
  Vision-language models (VLMs) achieve remarkable success in single-image tasks.<n>Real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline.<n>We propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs'perception, comprehension, and reasoning abilities in multi-image scenarios.
  arXiv  Detail & Related papers  (2025-04-28T19:02:18Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings.<n>EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
  We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references. Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
  arXiv  Detail & Related papers  (2024-03-05T13:45:46Z)
• PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter [21.45490901191175]
  PaLM2-VAdapter employs a progressively aligned language model as the vision-language adapter. Our method achieves these advancements with 3070% fewer parameters than the state-of-the-art large vision-language models.
  arXiv  Detail & Related papers  (2024-02-16T18:54:47Z)
• Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning [27.544311403607786]
  We introduce the Ziya-Visual series, a set of bilingual large-scale vision-language models (LVLMs) Our models adopt the Querying Transformer from BLIP-2, further exploring the assistance of optimization schemes. In addition, we stimulate the understanding ability of GPT-4 in multi-modal scenarios, translating our gathered English image-text datasets into Chinese.
  arXiv  Detail & Related papers  (2023-10-12T09:39:17Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)

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.