# LoTLIP: Improving Language-Image Pre-training for Long Text Understanding

arXiv: https://arxiv.org/abs/2410.05249 · HTML: https://mlsanity.com/paper/2410.05249/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 7 Oct 2024.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [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)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models](https://mlsanity.com/paper/2401.05252/) (2024)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions](https://mlsanity.com/paper/2312.08578/) (2023)
- [DreamLIP: Language-Image Pre-training with Long Captions](https://mlsanity.com/paper/2403.17007/) (2024)
- [SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?](https://mlsanity.com/paper/2402.01832/) (2024)
- [ImageInWords: Unlocking Hyper-Detailed Image Descriptions](https://mlsanity.com/paper/2405.02793/) (2024)
- [UniCLIP: Unified Framework for Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2209.13430/) (2022)
- [Context-Aware Visual Policy Network for Fine-Grained Image Captioning](https://mlsanity.com/paper/1906.02365/) (2019)

## Built on by (most cited first, 27 of 27)

- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [FG-CLIP: Fine-Grained Visual and Textual Alignment](https://mlsanity.com/paper/2505.05071/) (2025)
- [FLAIR: VLM with Fine-grained Language-informed Image Representations](https://mlsanity.com/paper/2412.03561/) (2024)
- [Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning](https://mlsanity.com/paper/2412.08614/) (2024)
- [Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension](https://mlsanity.com/paper/2412.03704/) (2024)
- [FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs](https://mlsanity.com/paper/2504.01916/) (2025)
- [COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training](https://mlsanity.com/paper/2412.01814/) (2024)
- [Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2509.19244/) (2025)
- [Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation](https://mlsanity.com/paper/2504.09479/) (2025)
- [SmartCLIP: Modular Vision-language Alignment with Identification Guarantees](https://mlsanity.com/paper/2507.22264/) (2025)
- [Aligned Better, Listen Better for Audio-Visual Large Language Models](https://mlsanity.com/paper/2504.02061/) (2025)
- [FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text](https://mlsanity.com/paper/2507.10095/) (2025)
- [Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching](https://mlsanity.com/paper/2503.14953/) (2025)
- [VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions](https://mlsanity.com/paper/2508.02329/) (2025)
- [DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignment](https://mlsanity.com/paper/2503.19311/) (2025)
- [SuperCLIP: CLIP with Simple Classification Supervision](https://mlsanity.com/paper/2512.14480/) (2025)
- [HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment](https://mlsanity.com/paper/2511.06653/) (2025)
- [EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval](https://mlsanity.com/paper/2412.00139/) (2024)
- [GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval](https://mlsanity.com/paper/2509.23370/) (2025)
- [ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder](https://mlsanity.com/paper/2510.18795/) (2025)
- [LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval](https://mlsanity.com/paper/2511.06268/) (2025)
- [Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding](https://mlsanity.com/paper/2602.02977/) (2026)
- [Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models](https://mlsanity.com/paper/2604.12391/) (2026)
- [Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs](https://mlsanity.com/paper/2509.19207/) (2025)
- [SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment](https://mlsanity.com/paper/2511.01390/) (2025)
- [GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining](https://mlsanity.com/paper/2603.24804/) (2026)
- [Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval](https://mlsanity.com/paper/2608.18521/) (2026)

## Abstract (arXiv)

Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key reason causing such an issue is that the training images are usually paired with short captions, leaving certain tokens easily overshadowed by salient tokens. Towards this problem, our initial attempt is to relabel the data with long captions, however, directly learning with which may lead to performance degradation in understanding short text (e.g., in the image classification task). Then, after incorporating corner tokens to aggregate diverse textual information, we manage to help the model catch up to its original level of short text understanding yet greatly enhance its capability of long text understanding. We further look into whether the model can continuously benefit from longer captions and notice a clear trade-off between the performance and the efficiency. Finally, we validate the effectiveness of our approach using a self-constructed large-scale dataset, which consists of 100M long caption oriented text-image pairs. Our method demonstrates superior performance in long-text-image retrieval tasks. The project page is available at https://wuw2019.github.io/lot-lip.