# EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data

arXiv: https://arxiv.org/abs/2605.19130 · HTML: https://mlsanity.com/paper/2605.19130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 49 of its 70 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Teaching CLIP to Count to Ten](https://mlsanity.com/paper/2302.12066/) (2023)
- [SONAR: Sentence-Level Multimodal and Language-Agnostic Representations](https://mlsanity.com/paper/2308.11466/) (2023)
- [PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding](https://mlsanity.com/paper/2504.13180/) (2025)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Temporal Alignment Networks for Long-term Video](https://mlsanity.com/paper/2204.02968/) (2022)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning](https://mlsanity.com/paper/2312.06722/) (2023)

## Abstract (arXiv)

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated web data fail to generalize to the sparse, weakly-aligned egocentric streams produced by wearable devices, embodied agents, and infant head-cams -- and no fixed evaluation pipeline exists for measuring progress on this regime. We train VLMs on datasets with varying degrees of semantic alignment between visual and linguistic inputs, including naturalistic infant and adult egocentric videos, and evaluate them with a comprehensive suite spanning multimodal language grounding and unimodal vision and language tasks. At the core of this suite is Machine-DevBench, a corpus-grounded benchmark of lexical and grammatical competence, automatically generated from the model's training vocabulary across logarithmic frequency bins to eliminate the train/eval mismatch and low statistical power of prior developmental benchmarks. Our results show that current VLM paradigms hinge on the tight semantic alignment of curated data and fail to exploit the weakly-aligned signal that dominates naturalistic egocentric input -- the very regime in which humans thrive. To motivate progress, we introduce the EgoBabyVLM Challenge to drive the development of models capable of grounded language learning from the kind of naturalistic data that human infants experience.