Florenz: Scaling Laws for Systematic Generalization in Vision-Language Models

• URL: http://arxiv.org/abs/2503.09443v1
• Date: Wed, 12 Mar 2025 14:41:10 GMT
• Title: Florenz: Scaling Laws for Systematic Generalization in Vision-Language Models
• Authors: Julian Spravil, Sebastian Houben, Sven Behnke,
• Abstract summary: Cross-lingual transfer enables vision-language models to perform vision tasks in various languages with training data only in one language.<n>Current approaches rely on large pre-trained multilingual language models.<n>We propose Florenz, a monolingual encoder-decoder VLM with 0.4B to 11.2B parameters combining the pre-trained VLM Florence-2 and the large language model Gemma-2.
• Score: 17.444066202370397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-lingual transfer enables vision-language models (VLMs) to perform vision tasks in various languages with training data only in one language. Current approaches rely on large pre-trained multilingual language models. However, they face the curse of multilinguality, sacrificing downstream task performance for multilingual capabilities, struggling with lexical ambiguities, and falling behind recent advances. In this work, we study the scaling laws of systematic generalization with monolingual VLMs for multilingual tasks, focusing on the impact of model size and seen training samples. We propose Florenz, a monolingual encoder-decoder VLM with 0.4B to 11.2B parameters combining the pre-trained VLM Florence-2 and the large language model Gemma-2. Florenz is trained with varying compute budgets on a synthetic dataset that features intentionally incomplete language coverage for image captioning, thus, testing generalization from the fully covered translation task. We show that not only does indirectly learning unseen task-language pairs adhere to a scaling law, but also that with our data generation pipeline and the proposed Florenz model family, image captioning abilities can emerge in a specific language even when only data for the translation task is available. Fine-tuning on a mix of downstream datasets yields competitive performance and demonstrates promising scaling trends in multimodal machine translation (Multi30K, CoMMuTE), lexical disambiguation (CoMMuTE), and image captioning (Multi30K, XM3600, COCO Karpathy).

Related papers

• LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining [2.6638517946494535]
  We propose a multilingual training paradigm LDP (Language Decoupled Pre-training) for better utilization of monolingual pre-training data.<n>Our proposed model LDM is first pre-trained on the language-independent data, where the language knowledge is decoupled by a diffusion model, and then the LDM is fine-tuned on the downstream languages.
  arXiv  Detail & Related papers  (2024-12-19T07:31:40Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• ICU: Conquering Language Barriers in Vision-and-Language Modeling by Dividing the Tasks into Image Captioning and Language Understanding [1.9906814758497542]
  ICU, Image Caption Understanding, divides a V&L task into two stages: a V&L model performs image captioning in English, and a multilingual language model (mLM) takes the caption as the alt text and performs cross-lingual language understanding. We show that ICU can achieve new state-of-the-art results for five languages, and comparable results for the rest.
  arXiv  Detail & Related papers  (2023-10-19T07:11:48Z)
• mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs [50.17767479660832]
  Vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to understand' the image input. We present mBLIP, the first Vision-LLM leveraging multilingual LLMs, which we obtain in a computationally efficient manner on consumer-level hardware.
  arXiv  Detail & Related papers  (2023-07-13T17:51:58Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data [2.225882303328135]
  We propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parsing task. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems.
  arXiv  Detail & Related papers  (2021-09-09T14:51:11Z)
• UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training [52.852163987208826]
  UC2 is the first machine translation-augmented framework for cross-lingual cross-modal representation learning. We propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM) Our proposed framework achieves new state-of-the-art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.
  arXiv  Detail & Related papers  (2021-04-01T08:30:53Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)
• Beyond English-Centric Multilingual Machine Translation [74.21727842163068]
  We create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. Our focus on non-English-Centric models brings gains of more than 10 BLEU when directly translating between non-English directions while performing competitively to the best single systems of WMT.
  arXiv  Detail & Related papers  (2020-10-21T17:01:23Z)

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.