AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Factorizing Perception and Policy for Interactive Instruction Following

Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim, Roozbeh Mottaghi, Jonghyun Choi

ICCV 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 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
add factorized perception and policy streams (ablation)MOCA · ALFRED val seentask success rate: 22.32 -> 25.85Improved
add factorization when data augmentation is absent (ablation)MOCA · ALFRED val seentask success rate: 12.56 -> 15.85Improved
add data augmentation (ablation)MOCA · ALFRED val seentask success rate: 15.85 -> 25.85Improved
add language-guided dynamic filters (ablation)MOCA · ALFRED val seentask success rate: 14.63 -> 15.85Improved
add language-guided dynamic filters (ablation)MOCA · ALFRED val unseentask success rate: 2.19 -> 2.92Improved
add object-centric localisation (ablation)MOCA · ALFRED val seentask success rate: 3.90 -> 15.85Improved
add object-centric localisation with factorization (ablation)MOCA · ALFRED val seentask success rate: 11.71 -> 14.63Improved
add instance association (ablation)MOCA · ALFRED val seentask success rate: 23.66 -> 25.85Improved
add obstruction evasion (ablation)MOCA · ALFRED val seentask success rate: 20.00 -> 25.85Improved
feed goal and instructions concatenated to IPM (ablation)MOCA · ALFRED val seentask success rate: 25.85 -> 29.76Mixed
feed goal and instructions concatenated to APM (ablation)MOCA · ALFRED val unseentask success rate: 5.36 -> 5.36No clear effect
feed goal and instructions concatenated to both streams (ablation)MOCA · ALFRED val seentask success rate: 25.85 -> 26.34No clear effect

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