ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting

• URL: http://arxiv.org/abs/2604.18452v1
• Date: Mon, 20 Apr 2026 16:10:28 GMT
• Title: ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting
• Abstract summary: We show that two-tower encoder models are superior to one-tower encoders in low-resource settings for discriminative English tasks.<n>We also present ESsEN, a compact vision-language model that can be trained end-to-end with relatively few resources.
• Score: 0.8307668828380427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language modeling is rapidly increasing in popularity with an ever expanding list of available models. In most cases, these vision-language models have parameters in the tens of billions, which is necessary for some needs, but in many cases smaller models are necessary (e.g., on edge devices or independent robotic platforms). Unfortunately, there is little research in producing light-weight models or in training them with small datasets. Inspired by the language learning progression and data sparsity in child development, in this paper, we address both of these goals in a systematic fashion. We show that two-tower encoder models are superior to one-tower encoders in low-resource settings for discriminative English tasks. We show also that incorporating traditional convolutional networks into the two-tower transformer architecture can help produce parameter efficient vision-language models. Finally, we show that the cross-modal fusion module of two-tower encoders can vary significantly in shape and size while producing the same results. In addition, we present ESsEN, a compact vision-language model that can be trained end-to-end with relatively few resources that performs as well on several tasks with only a fraction of the parameters compared to other models. The experimental results and the tools we present here make vision-language modeling more accessible to a wider variety of researchers.

Related papers

• M*: A Modular, Extensible, Serving System for Multimodal Models [62.77975969000349]
  We present M*, a universal serving system for efficient serving of composite AI models.<n>We show how it can concisely capture composite models from a broad range of families.<n>M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x.
  arXiv  Detail & Related papers  (2026-06-10T21:22:22Z)
• Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality [74.59049806800176]
  This demo paper highlights the Tevatron toolkit's key features, bridging academia and industry.<n>We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness.<n>We also release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval.
  arXiv  Detail & Related papers  (2025-05-05T08:52:49Z)
• LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
  In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch. Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process. By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
  arXiv  Detail & Related papers  (2024-07-28T06:10:47Z)
• TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones [18.954681684239358]
  This study introduces TinyGPT-V, a novel open-source MLLM, designed for efficient training and inference across various vision-language tasks. With its language model 2.8 billion parameters, TinyGPT-V achieves comparable results in VQA and image inference tasks to its larger counterparts.
  arXiv  Detail & Related papers  (2023-12-28T07:11:41Z)
• Language Resources for Dutch Large Language Modelling [0.0]
  We introduce two fine-tuned variants of the Llama 2 13B model. We provide a leaderboard to keep track of the performance of (Dutch) models on a number of generation tasks.
  arXiv  Detail & Related papers  (2023-12-20T09:06:06Z)
• Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning [60.26952378997713]
  Contrastive vision-language models (e.g. CLIP) are created by updating all the parameters of a vision model and language model through contrastive training. We show that a minimal set of parameter updates ($$7%) can achieve the same performance as full-model training. We describe a series of experiments: we show that existing knowledge is conserved more strongly in parameter-efficient training.
  arXiv  Detail & Related papers  (2023-03-21T14:12:08Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Language Models are General-Purpose Interfaces [109.45478241369655]
  We propose to use language models as a general-purpose interface to various foundation models. A collection of pretrained encoders perceive diverse modalities (such as vision, and language) We propose a semi-causal language modeling objective to jointly pretrain the interface and the modular encoders.
  arXiv  Detail & Related papers  (2022-06-13T17:34:22Z)

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.