# PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?

arXiv: https://arxiv.org/abs/2502.04192 · HTML: https://mlsanity.com/paper/2502.04192/

## Key facts

- Cited by 4 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 28 of its 37 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## 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, 28 of 28)

- [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)
- [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)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models](https://mlsanity.com/paper/2312.02949/) (2023)
- [Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2404.08181/) (2024)
- [POSIX: A Prompt Sensitivity Index For Large Language Models](https://mlsanity.com/paper/2410.02185/) (2024)
- [F-LMM: Grounding Frozen Large Multimodal Models](https://mlsanity.com/paper/2406.05821/) (2024)
- [Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models](https://mlsanity.com/paper/2311.17095/) (2023)
- [Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision](https://mlsanity.com/paper/2410.08209/) (2024)

## Built on by (most cited first, 4 of 4)

- [SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories](https://mlsanity.com/paper/2503.08625/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation](https://mlsanity.com/paper/2601.03054/) (2026)
- [PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?](https://mlsanity.com/paper/2509.02807/) (2025)

## Abstract (arXiv)

Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current trend is to train MLLMs with pixel-level grounding supervision in terms of masks on large-scale labelled data and specialized decoders for the segmentation task. However, we show that such MLLMs when evaluated on recent challenging vision-centric benchmarks, exhibit a weak ability in visual question answering (VQA). Surprisingly, some of these methods even downgrade the grounding ability of MLLMs that were never trained with such pixel-level supervision. In this work, we propose two novel challenging benchmarks with paired evaluation for both VQA and grounding. We demonstrate that simple baselines that are not unified achieve performance that matches or surpasses some of the pixel-level MLLMs. Our paired benchmarks and evaluation enable additional analysis on the reasons for failure with respect to VQA and/or grounding. Furthermore, we propose a prompt sensitivity analysis on both the language and visual prompts tailored for the grounding task. More importantly, we study the research question of ``When does grounding emerge in MLLMs with respect to the output tokens?'' We propose an interpretability tool that can be plugged into any MLLM to study the aforementioned question. We show that grounding does not necessarily coincide with the exact referring expression in the output, but can coincide with the object parts, its location, appearance, context or state. Code and datasets are publicly available at https://msiam.github.io/PixFoundationSeries/.