VLMs show partial alignment with children's performance on six cognitive tasks, with stronger models matching better at task and item levels but struggling on matrix reasoning and mental rotation.
On the robustness of modeling grounded word learning through a child’s egocentric input.arXiv preprint arXiv:2507.14749, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
BabyCL learns word-referent mappings from egocentric video in a single chronological pass via streaming visual learning, dual replay, and three contrastive losses, outperforming streaming baselines on the SAYCam 4AFC benchmark.
Current VLMs depend on tightly aligned curated data and cannot exploit the weakly-aligned egocentric video signals that dominate naturalistic infant input.
citing papers explorer
-
LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")
VLMs show partial alignment with children's performance on six cognitive tasks, with stronger models matching better at task and item levels but struggling on matrix reasoning and mental rotation.
-
Continual Visual and Verbal Learning Through a Child's Egocentric Input
BabyCL learns word-referent mappings from egocentric video in a single chronological pass via streaming visual learning, dual replay, and three contrastive losses, outperforming streaming baselines on the SAYCam 4AFC benchmark.
-
EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data
Current VLMs depend on tightly aligned curated data and cannot exploit the weakly-aligned egocentric video signals that dominate naturalistic infant input.