Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs

[2608.15085] Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2608.15085 (cs) [Submitted on 15 Aug 2026] Title: Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs Authors: Yihang Du , Juhao Liang , Zhengzhao Lai , Siyu Li , Yan Hu View a PDF of the paper titled Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs, by Yihang Du and 4 other authors View PDF HTML (experimental) Abstract: Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their text-only backbones. While mechanistic evidence from text-only models suggests that non-English inputs are routed through an English-centric latent space, the multimodal implications of this phenomenon remain unexplored. Through rigorous mechanistic analysis, we identify the \textbf{Ghost Anchor} phenomenon: a temporal modality asynchrony where linguistic translation to the English semantic manifold completes in early layers, while visual semanticization remains immature. Consequently, visual signals are physically present yet functionally invisible during the early alignment window. To rectify this, we propose \textbf{ANCHOR}, a training framework employing Proactive Visual Anchoring (PVA) to accelerate early visual semantic emergence, ensuring visual representations proactively guide linguistic translation. Mechanistic interventions confirm that ANCHOR successfully restores the causal influence of visual signals during early translation. Furthermore, extensive experiments on XMMMU, MaXM, and CVQA demonstrate that ANCHOR consistently outperforms standard baselines, achieving robust visual reasoning across both fine-tuned and zero-shot languages. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.15085 [cs.CL] (or arXiv:2608.15085v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.15085 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhengzhao Lai [ view email ] [v1] Sat, 15 Aug 2026 07:04:53 UTC (13,265 KB) Full-text links: Access Paper: View a PDF of the paper titled Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs, by Yihang Du and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs#611035
• Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict#819989
• Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision#1116282
• Human-Centric Image Captioning with Subject-Centered Spatial Understanding#985668
• Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference#10366