Let ViT Speak: Generative Language-Image Pre-training

• URL: http://arxiv.org/abs/2605.00809v1
• Date: Fri, 01 May 2026 17:51:38 GMT
• Title: Let ViT Speak: Generative Language-Image Pre-training
• Abstract summary: GenLIP is a minimalist generative pretraining framework for Vision Transformers (ViTs)<n>It trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective.<n>It achieves competitive or superior results across diverse multimodal benchmarks.
• Score: 102.76320739909421
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \textbf{Simplicity}: a single transformer jointly models visual and textual tokens; (2) \textbf{Scalability}: it scales effectively with both data and model size; and (3) \textbf{Performance}: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.

Related papers

• HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models [15.877790469608662]
  We introduce an LVLM-driven data refinement pipeline to enhance the quality of image-text pair data.<n>We propose a training paradigm that extends conventional contrastive learning by incorporating negative descriptions and short tags.<n>Our approach achieves state-of-the-art performance in zero-shot classification, cross-modal retrieval, and fine-grained visual understanding tasks.
  arXiv  Detail & Related papers  (2025-07-30T07:21:36Z)
• Compile Scene Graphs with Reinforcement Learning [69.36723767339001]
  Next-token prediction is the fundamental principle for training large language models (LLMs)<n>We introduce R1-SGG, a multimodal LLM (M-LLM) initially trained via supervised fine-tuning (SFT) on the scene graph dataset.<n>We design a set of graph-centric rewards, including three recall-based variants -- Hard Recall, Hard Recall+Relax, and Soft Recall.
  arXiv  Detail & Related papers  (2025-04-18T10:46:22Z)
• TULIP: Towards Unified Language-Image Pretraining [60.99500935831526]
  We introduce T, an open-source, drop-in replacement for existing CLIP-like models.<n>Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features.<n>Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across benchmarks.
  arXiv  Detail & Related papers  (2025-03-19T17:58:57Z)
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features [48.11426546401525]
  We introduce SigLIP 2, a family of new multilingual vision-language encoders.<n>We extend the original image-text training objective with several prior, independently developed techniques into a unified recipe.<n>New training recipe leads to significant improvements on localization and dense prediction tasks.
  arXiv  Detail & Related papers  (2025-02-20T18:08:29Z)
• Enhancing Vision-Language Model with Unmasked Token Alignment [37.12838142681491]
  This paper introduces Unmasked Token Alignment (UTA), a method that leverages existing CLIP models to further enhance its vision-language representations. UTA trains a Vision Transformer (ViT) by aligning unmasked visual tokens to the corresponding image tokens from a frozen CLIP vision encoder, which automatically aligns the ViT model with the CLIP text encoder.
  arXiv  Detail & Related papers  (2024-05-29T11:48:17Z)
• VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation [79.02357561313785]
  We introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for both image and text modalities by employing a straightforward auto-regressive objective.
  arXiv  Detail & Related papers  (2023-12-14T18:59:43Z)
• VILA: On Pre-training for Visual Language Models [74.08039416548209]
  We study the design options for VLM pre-training through step-by-step controllable comparisons. We build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-12T18:58:18Z)
• EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE [66.48689706116808]
  Efficient Vision-languagE is one unified multimodal Transformer pre-trained solely by one unified pre-training task. Eve encodes both vision and language within a shared Transformer network integrated with modality-aware sparse Mixture-of-Experts. Eve achieves state-of-the-art performance on various vision-language downstream tasks, including visual question answering, visual reasoning, and image-text retrieval.
  arXiv  Detail & Related papers  (2023-08-23T07:36:30Z)
• ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training [29.240131406803794]
  We show that a common space can be created without any training at all, using single-domain encoders and a much smaller amount of image-text pairs. Our model has unique properties, most notably, deploying a new version with updated training samples can be done in a matter of seconds.
  arXiv  Detail & Related papers  (2022-10-04T16:56:22Z)

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.