Federico Tombari, Bernt Schiele, Jiahao Xie, Nathalie Rauschmayr, Alessio Tonioni
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1. Test-time visual in-context tuning (VICT) on six representative vision tasks under distribution shifts. We benchmark the robustness of VICL with 15 common corruptions adopted in [23,31], and report the averaged performance across all corruptions. Existing VICL models like Painter exhibit poor generalization capability to unseen new domains when the task prompts come from the training distribution (i.e., zero-shot). Performances are even worse when given task prompts from the test distribution (i.e., one-shot). By performing VICT at test time, we can significantly improve Painter in both zero-shot and one-shot manners.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.21777")
get_code_for_paper("2503.21777")
have("2503.21777")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2503.21777.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2503.21777)
Connect an agent — have() is free.