Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling

• URL: http://arxiv.org/abs/2510.08470v1
• Date: Thu, 09 Oct 2025 17:10:36 GMT
• Title: Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
• Authors: Bianca-Mihaela Ganescu, Suchir Salhan, Andrew Caines, Paula Buttery,
• Abstract summary: Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information.<n>We propose a lightweight decoder-based architecture with token-wise dynamic gating for adaptive fusion of linguistic and visual cues.
• Score: 3.5408685781175016
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight decoder-based architecture with (1) token-wise dynamic gating for adaptive fusion of linguistic and visual cues, (2) feature modulation and channel attention to maximise the utility of limited visual information and (3) auxiliary contrastive objectives for visual grounding. Evaluation on five benchmarks (BLiMP, BLiMP Supplement, EWoK, Winoground and VQA) shows competitive or superior performance to multimodal baselines. More notably, our dynamic gate discovers interpretable patterns without explicit supervision, favouring visual cues for content words and linguistic cues for function words. While we identify limitations in the Challenge constraints, such as the information bottleneck created by global image embeddings and training instability from the dataset split, our findings establish dynamic gating as a powerful tool for efficient multimodal learning, offering both interpretability and performance even under severe constraints.

Related papers

• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• True Multimodal In-Context Learning Needs Attention to the Visual Context [69.63677595066012]
  Multimodal Large Language Models (MLLMs) have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks.<n>Current MLLMs tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation.<n>We introduce Dynamic Attention Reallocation (DARA), an efficient fine-tuning strategy that encourages models to attend to the visual context.
  arXiv  Detail & Related papers  (2025-07-21T17:08:18Z)
• FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability [10.184567639685321]
  We introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding.<n>We present benchmarks to assess the model's ability to use image as substantive evidence.<n>We identify attention heads with the strongest vision-language alignment, enabling explainability on visual-driven hallucinations.
  arXiv  Detail & Related papers  (2024-12-19T09:24:10Z)
• MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding [6.538592344967826]
  We introduce MUSE-VL, a Unified Vision-Language Model Semantic through discrete semantic.<n>Our method improved the understanding performance by 4.8% compared to the previous SOTA Emu3 and surpassed the dedicated understanding model LLaVA-NeXT 34B by 3.7%.
  arXiv  Detail & Related papers  (2024-11-26T03:33:52Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Divert More Attention to Vision-Language Object Tracking [87.31882921111048]
  We argue that the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning motivate us to design more effective vision-language representation for tracking. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer)
  arXiv  Detail & Related papers  (2023-07-19T15:22:06Z)
• 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.