# TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment

arXiv: https://arxiv.org/abs/2604.12012 · HTML: https://mlsanity.com/paper/2604.12012/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 54 of its 66 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (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)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)

## Built on by (most cited first, 13 of 13)

- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers](https://mlsanity.com/paper/2605.16745/) (2026)
- [4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes](https://mlsanity.com/paper/2610.03715/) (2026)
- [MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image](https://mlsanity.com/paper/2605.10616/) (2026)
- [LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute](https://mlsanity.com/paper/2605.06809/) (2026)
- [Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models](https://mlsanity.com/paper/2606.21292/) (2026)
- [VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining](https://mlsanity.com/paper/2607.02707/) (2026)
- [PAGE: Towards Practical Human-level Gaze Target Estimation](https://mlsanity.com/paper/2607.04860/) (2026)
- [Streaming Neural Speech Codecs through Time-Invariant Representations](https://mlsanity.com/paper/2607.05250/) (2026)
- [SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment](https://mlsanity.com/paper/2607.15058/) (2026)
- [Self-Supervised Learning of Structured Dynamics from Videos](https://mlsanity.com/paper/2607.21576/) (2026)
- [Foundational feature fusion for conditional flow matching in 6D pose estimation](https://mlsanity.com/paper/2608.29183/) (2026)
- [Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs](https://mlsanity.com/paper/2609.10346/) (2026)

## Abstract (arXiv)

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability that these models still struggle with is aligning dense patch representations with text embeddings of corresponding concepts. In this work, we investigate this critical issue and propose novel techniques to enhance this capability in foundational vision-language models. First, we reveal that a patch-level distillation procedure significantly boosts dense patch-text alignment -- surprisingly, the patch-text alignment of the distilled student model strongly surpasses that of the teacher model. This observation inspires us to consider modifications to pretraining recipes, leading us to propose iBOT++, an upgrade to the commonly-used iBOT masked image objective, where unmasked tokens also contribute directly to the loss. This dramatically enhances patch-text alignment of pretrained models. Additionally, to improve vision-language pretraining efficiency and effectiveness, we modify the exponential moving average setup in the learning recipe, and introduce a caption sampling strategy to benefit from synthetic captions at different granularities. Combining these components, we develop TIPSv2, a new family of image-text encoder models suitable for a wide range of downstream applications. Through comprehensive experiments on 9 tasks and 20 datasets, we demonstrate strong performance, generally on par with or better than recent vision encoder models. Code and models are released via our project page at https://gdm-tipsv2.github.io/ .