A2A-Bench's

Affordance2Action: Task-Conditioned Scene-level Affordance Grounding for Real-Time Manipulation

new Abstract: Task-conditioned manipulation requires grounding instructions to task-relevant functional parts rather than object categories. This setting is scene-dependent and often one-to-many in cluttered scenes: the same object may afford different interactions across tasks, while a single task may correspond to either one functional region or multiple valid functional regions, depending on the scene layout. Existing affordance datasets and benchmarks remain misaligned with this setting,...