AI Paper Atlas

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

A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Rongtao Xu, Jian Zhang, Minghao Guo, Youpeng Wen, Haoting Yang, Min Lin, Jianzheng Huang, Zhe Li, Kaidong Zhang, Liqiong Wang, Yuxuan Kuang, Meng Cao and 2 more

ICCV 2025 · 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
add Position Offset Attention (ablation)A0-1B · Maniskill-5k offlineMAE: 6.3 -> 5.5Improved
add Position Offset Attention (ablation)A0-1B · HOI4D-22k offlineMAE: 47.9 -> 47.5Improved
add Position Offset Attention (ablation)A0-1B · DROID-3k offlineMAE: 18.5 -> 17.5Improved
add Spatial Information Aggregation Layer (ablation)A0-1B · HOI4D-22k offlineMAE: 61.1 -> 47.5Improved
add Spatial Information Aggregation Layer (ablation)A0-1B · Maniskill-5k offlineMAE: 10.2 -> 5.5Improved
add Spatial Information Aggregation Layer (ablation)A0-1B · DROID-3k offlineMAE: 19.6 -> 17.5Improved
add pre-training on 1M PixMo-One-Point contact points (ablation)A0-1B · HOI4D, DROID, ManiSkill offline transferMAEImproved
use A0 instead of Robopoint for first contact pointRobopoint · HOI4D first-point MAEMAE: 121.09 -> 54.46Improved
use A0 instead of Robopoint for first contact pointRobopoint · DROID first-point MAEMAE: 27.47 -> 14.13Improved
use A0-1B instead of Molmo points with the same action execution moduleMolmo · Franka real-world (4 tasks, avg success)success rate (%): 43.75 -> 62.50Improved
use A0-1B instead of MOKA on KinovaMOKA · Kinova real-world (4 tasks, avg success)success rate (%): 45.00 -> 53.75Improved
use A0-1B instead of MOKA/ReKep for Place ObjectMOKA · Kinova Place Objectsuccess rate (%): 70 -> 60Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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