AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

Karmesh Yadav, Yusuf Ali, Gunshi Gupta, Yarin Gal, Zsolt Kira

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
supervised fine-tune the VLM on FindingDory training dataQwen2.5-VL · FindingDory high-level tasksHL success rate: average improvement of 25% across tasksImproved
add FindingDory SFT data to Video-R1 SFT (ablation)Video-R1 · VSI-BenchMCQ accuracy: 33.33 -> 35.06Improved
add FindingDory SFT data to Video-R1 SFT (ablation)Video-R1 · VSI-Benchnumerical accuracy: 32.67 -> 32.35No clear effect
add FindingDory data to GRPO training (ablation)Video-R1 · VSI-BenchMCQ accuracy: 33.57 -> 35.42Improved
add FindingDory data to GRPO training (ablation)Video-R1 · VSI-Benchnumerical accuracy: 33.9 -> 34.82Improved
increase number of input video frames for frozen VLMs (ablation)frozen VLMs · FindingDory high-level tasksHL success rateNo clear effect
train SFT model with longer (subsampled) videos (ablation)Qwen SFT · FindingDory high-level tasksHL success rateImproved
replace video input with textual memory summaries (ablation)Qwen2.5-VL text agent · FindingDory high-level tasksHL success rateHurt
decompose policy: add ImageNav low-level policy after high-level VLM (ablation)Qwen2.5-VL-7B hierarchical agent · FindingDoryLL-SRHurt
use mapping-based instead of ImageNav low-level policy (ablation)Qwen2.5-VL-7B hierarchical agent · FindingDoryLL-SR: only 25% relative drop in SRImproved
subsample videos to 96 frames (ablation)FindingDory tasks · FindingDory solvabilitytask solvability: approx 1% dropHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy