AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction

ArXi:2604.01371v1 Announce Type: new Surgical action automation has progressed rapidly toward achieving surgeon-like dexterous control, driven primarily by advances in learning from nstration and vision-language-action models. While these have nstrated success in table-top experiments, translating them to clinical deployment remains challenging: current methods offer limited predictability on where instruments will interact on tissue surfaces and lack explicit conditioning inputs to enforce tool-action-specific safe interaction regions. Addressing this gap, we.