findingdory-habitat

2026 ICLR Submission Current vision-language models (VLMs) struggle with long-term memory in embodied tasks. To address this, we introduce FindingDory, a benchmark in Habitat that evaluates memory-based reasoning across 60 long-horizon tasks. In this repo, we release the FindingDory Habitat Dataset. The episode dataset is used to run online evaluations with the Habitat simulator using VLM-based navigation agents. Each episode involves a robot performing multiple pick-place object… See the full description on the dataset page: https://huggingface.co/datasets/findingdory/findingdory-habitat.