Kevin Lu(@_kevinlu):encouraging progress on continued test-time adaptation beyond model deployment! very excited about the future of personalized models, and developing reliable, easy-to-use pipelines to enable robust & personalized intelligence i think the "no TTT" baseline from Section 4.5 is particularly neat, justifying training with gradient steps at test time

2026.01.22 21:22

encouraging progress on continued test-time adaptation beyond model deployment! very excited about the future of personalized models, and developing reliable, easy-to-use pipelines to enable robust & personalized intelligence i think the "no TTT" baseline from Section 4.5 is particularly neat, justifying training with gradient steps at test time