AI Paper Atlas

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

Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues

Francesco Taioli, Edoardo Zorzi, Gianni Franchi, Alberto Castellini, Alessandro Farinelli, Marco Cristani, Yiming Wang

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 10 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
add the Self-Questioner and Skip-Question together to AIUTA (ablation)AIUTA · CoIN ablation splitSR: 9.21 -> 14.47Improved
add only the Self-Questioner (no Skip-Question) (ablation)AIUTA · CoIN ablation splitSR: 9.21 -> 9.87Improved
add only Skip-Question (no Self-Questioner) (ablation)AIUTA · CoIN ablation splitSR: 9.21 -> 8.55Hurt
add Skip-Question when Self-Questioner is on (ablation)AIUTA · CoIN ablation splitNQ: 4.6 -> 1.68Improved
add user interaction via AIUTA on top of zero-shot VLFMVLFM · CoIN-Bench Val Seen SynonymsSR: 0.00 -> 14.38Improved
use AIUTA instead of trained baselines on unseen categoriesAIUTA · CoIN-Bench Val UnseenSR: 2.61 -> 6.67 (vs OVON)Improved
training-free AIUTA versus OVON trained on GOAT-Bench on seen-synonym categoriesAIUTA · CoIN-Bench Val Seen SynonymsSR: 15.88 -> 14.38Hurt
replace real human with VLM-simulated user (ablation)AIUTA · CoIN-Bench subset (40 episodes)SR: 42.50 -> 42.50No clear effect
use Normalized Entropy instead of Energy Score for VLM uncertainty (ablation)AIUTA Self-Questioner · IDKVQAEffective Reliability Phi_c=1: 20.45 -> 21.12Improved
use Normalized Entropy instead of MaxProb for uncertainty (ablation)AIUTA Self-Questioner · IDKVQAEffective Reliability Phi_c=1: 15.94 -> 21.12Improved
use Normalized Entropy threshold instead of Energy Score threshold under data scarcityuncertainty threshold tau · IDKVQA subsamplednormalized Phi_c=1 sensitivityImproved

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