AI Paper Atlas

Research map / Video / Video-language understanding

Compositional Foundation Models for Hierarchical Planning

Anurag Ajay, Seungwook Han, Yilun Du, Shuang Li, Abhi Gupta, Tommi S. Jaakkola, Joshua B. Tenenbaum, Leslie Pack Kaelbling, Akash Srivastava, Pulkit Agrawal

NeurIPS 2023 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 2 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
compose task, visual, and action planning hierarchicallyHiP · Paint-block, Object-arrange, and Kitchen-tasks (seen and unseen)task/subtask completion rate: Paint-block: 74.3\pm1.9 (seen), 72.8\pm1.7 (unseen); Object-arrange: 75\pm2.8, 75.4\pm2.6; Kitchen-tasks: 85.8\pm 9.4, 8Improved
use oracle subgoals instead of predicted subgoals (ablation)HiP · Paint-block, Object-arrange, and Kitchen-taskstask/subtask completion rate: Paint-block: 74.3\pm1.9 -> \bf{81.2}\pm1.8 (seen); 72.8\pm1.7 -> \bf{79.6}\pm1.9 (unseen)Improved
remove task-plan refinement for visual grounding (ablation)HiP · Paint-blocktask completion rateHurt
remove both task-plan and visual-plan refinement (ablation)HiP · Paint-blocktask completion rateHurt
remove visual-plan refinement (ablation)HiP · Paint-blocktask completion rateHurt
pretrain video diffusion on Ego4D (ablation)HiP video planner · Long-horizon planningsuccess rateImproved
pretrain video diffusion on Ego4D (ablation)HiP video planner · Long-horizon planningFVDImproved
initialize inverse dynamics with VC-1 weights instead of random initialization (ablation)HiP inverse dynamics · Paint-block and Object-arrangemean squared error: 1K labeled robotic trajectories vs 10K labeled robotic trajectoriesImproved
initialize inverse dynamics with VC-1 weights instead of random initialization (ablation)HiP inverse dynamics · Kitchen-tasksmean squared error: 3.5k labeled robotic trajectories vs 10K labeled robotic trajectoriesImproved
replace the learned subgoal classifier with frozen MiniGPT-4 (ablation)HiP task planner · Paint-blocksubgoal prediction accuracyNo clear effect
replace the learned subgoal classifier with frozen MiniGPT-4 (ablation)HiP task planner · Object-arrangesubgoal prediction accuracyHurt

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