AI Paper Atlas

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

AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Affordance Correspondence

Jiawei Zhang, Kaizhe Hu, Yingqian Huang, Yuanchen Ju, Zhengrong Xue, Huazhe Xu

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation

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
generate demonstrations over many unseen meshes via affordance correspondence instead of DemoGen single-object augmentationvisuomotor policy · Teapot Pouring (sim, unseen meshes)success rate: 0.131 -> 0.553Improved
use AffordGen instead of CPGen mesh stretchingvisuomotor policy · Mug Hanging (sim, unseen meshes)success rate: 0.502 -> 0.707Improved
spread 1000 demos over 1000 meshes with 1 demo each instead of fewer meshes (ablation)AffordGen · Teapot Pouring (sim, unseen meshes)success rate: 0.553 -> 0.242Hurt
increase meshes from 20x50 to 50x20 for teapot (ablation)AffordGen · Teapot Pouring (sim, unseen meshes)success rate: 0.353 -> 0.553Improved
vary mesh count under fixed 1000 demos on shoe task (ablation)AffordGen · Shoe Aligning (sim, unseen meshes)success rate: 0.438 (20x50), 0.302 (50x20), 0.588 (100x10), 0.425 (1000x1)Mixed
AffordGen training on generated data vs DemoGen on source meshvisuomotor policy · Teapot Pouring (sim, source mesh)success rate: 0.933 -> 0.960No clear effect
AffordGen vs CPGen on cross-category transfervisuomotor policy · Teapot to Mug cross-category (sim)success rate (%): 2.70 -> 55.00Improved
AffordGen closed-loop policy trained on generated data vs open-loop FUNCTO plannerreal-world mug hanging · Mug Hanging (real, unseen objects)successes/trials: 48/162 -> 107/162Improved
AffordGen vs CPGen on real knife cutting source objectvisuomotor policy · Knife Cutting (real, source mesh)successes/trials: 23/27 vs 23/27No clear effect
AffordGen vs CPGen on real shoe organizing source objectvisuomotor policy · Shoe Organizing (real, source mesh)successes/trials: 18/20 -> 11/20Hurt

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