AI Paper Atlas

Research map / Large language models / AI and society

🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

Matt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs, Kiana Ehsani, Jordi Salvador, Winson Han, Eric Kolve, Aniruddha Kembhavi, Roozbeh Mottaghi

NeurIPS 2022 · Large language models › AI and society · approach: Social-science view of AI evaluation

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
Pre-train on ProcTHOR and evaluate zero-shot instead of using the RoboTHOR-trained baselineObjectNav agent · RoboTHOR ChallengeSPL: 0.200 -> 0.237Improved
Fine-tune the ProcTHOR-pretrained model on benchmark training dataObjectNav agent · RoboTHOR ChallengeSPL: 0.237 -> 0.288Improved
Use ProcTHOR pre-training and fine-tune on the benchmarkObjectNav agent · Habitat Challenge 2022 (HM3D-Semantics)SPL: 0.055 -> 0.270; Large: 0.077 -> 0.318Mixed
Pre-train on ProcTHOR and evaluate zero-shot instead of using the AI2-iTHOR-trained baselineObjectNav agent · AI2-iTHOR ObjectNavSPL: 0.516 -> 0.644Improved
Fine-tune the ProcTHOR-pretrained model on benchmark training dataObjectNav agent · AI2-iTHOR ObjectNavSPL: 0.644 -> 0.621Hurt
Train on 10,000 generated houses instead of fewer houses (ablation)ProcTHOR ObjectNav agent · ProcTHOR ObjectNavSPL: 0.077 -> 0.185Improved
Train on 10,000 generated houses instead of fewer houses (ablation)ObjectNav agent · RoboTHOR Test (0-shot)SPL: 0.040 -> 0.210Improved
Train on 10,000 generated houses instead of fewer houses (ablation)ObjectNav agent · AI2-iTHOR Test (0-shot)SPL: 0.249 -> 0.554Improved
Use a larger CLIP backbone and wider RNN (ablation)ProcTHOR ObjectNav agent · Habitat Challenge 2022 (HM3D-Semantics)SPL: 0.055 -> 0.077Improved
Fine-tune the ProcTHOR-pretrained model on benchmark training dataRearrangement agent · 1-phase Rearrangement Challenge 2022% Fixed Strict: 0.156 -> 0.245Improved
Pre-train on ProcTHOR and evaluate zero-shot instead of using the iTHOR-SimpleConv baselineArmPointNav agent · ManipulaTHORSuccess: 29.2% -> 37.9%Improved

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