EMNLP paper: How VLMs map novel visual concepts to language vs humans
benno_krojer · x · 2026-08-21
The author shares a new paper accepted at EMNLP (Budapest), led by undergrad researcher Ada Tur, with bennokrojer as last author for the first time.
The study examines how vision-language models adopt new visual concepts (illustrated with a funny dog example) and compares how they map those concepts to language versus human learners — an empirical look at multimodal concept learning mechanisms.
More from Research
- 4DAnyone turns single monocular video into 4D human models — janusch_patas · 2026-08-21
- Academic study: agents without MCP match reliability and cost 5-28x less on mature CLI tasks — tobowers · 2026-08-21
- ICLR 2026 Paper Open Sources Efficient Probing Benchmark — ducha_aiki · 2026-08-21
- SFT Shifts Reasoning Language, RL Fixes Formatting in Low-Resource SFT — KIEFERSA · 2026-08-21
- GOAG: Object-Agnostic Generative Grasp Planner for Robots — Julien Merand · 2026-08-21
- CoToGrasp: Contact-Topology-Conditioned Zero-Shot Dexterous Grasping — Julien Merand · 2026-08-21