# FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

arXiv: https://arxiv.org/abs/2411.11927 · HTML: https://mlsanity.com/paper/2411.11927/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 69 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Builds on (most cited first, 30 of 62)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)

## Built on by (most cited first, 12 of 12)

- [Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs](https://mlsanity.com/paper/2504.17432/) (2025)
- [UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning](https://mlsanity.com/paper/2510.13515/) (2025)
- [Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving](https://mlsanity.com/paper/2509.22756/) (2025)
- [A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback](https://mlsanity.com/paper/2511.17255/) (2025)
- [Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs](https://mlsanity.com/paper/2602.05275/) (2026)
- [ReMoT: Reinforcement Learning with Motion Contrast Triplets](https://mlsanity.com/paper/2603.00461/) (2026)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)
- [ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder](https://mlsanity.com/paper/2510.18795/) (2025)
- [Illuminating Visual Identity in Universal Multimodal Embeddings](https://mlsanity.com/paper/2608.01794/) (2026)
- [SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs](https://mlsanity.com/paper/2604.13710/) (2026)
- [FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation](https://mlsanity.com/paper/2605.21832/) (2026)
- [Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling](https://mlsanity.com/paper/2605.22484/) (2026)

## Abstract (arXiv)

Language-image pre-training faces significant challenges due to limited data in specific formats and the constrained capacities of text encoders. While prevailing methods attempt to address these issues through data augmentation and architecture modifications, they continue to struggle with processing long-form text inputs, and the inherent limitations of traditional CLIP text encoders lead to suboptimal downstream generalization. In this paper, we propose FLAME (Frozen Large lAnguage Models Enable data-efficient language-image pre-training) that leverages frozen large language models as text encoders, naturally processing long text inputs and demonstrating impressive multilingual generalization. FLAME comprises two key components: 1) a multifaceted prompt distillation technique for extracting diverse semantic representations from long captions, which better aligns with the multifaceted nature of images, and 2) a facet-decoupled attention mechanism, complemented by an offline embedding strategy, to ensure efficient computation. Extensive empirical evaluations demonstrate FLAME's superior performance. When trained on CC3M, FLAME surpasses the previous state-of-the-art by 4.9% in ImageNet top-1 accuracy. On YFCC15M, FLAME surpasses the WIT-400M-trained CLIP by 44.4% in average image-to-text recall@1 across 36 languages, and by 34.6% in text-to-image recall@1 for long-context retrieval on Urban-1k. Code is available at https://github.com/MIV-XJTU/FLAME.