cba76ef96c4cd625631ab4d33285b045-Paper-Conference.pdf
–Neural Information Processing Systems
Learning disentangled and distributed representation ofgenerativefactors oftheworld isbelieved tobenefit compositional generalization, because those invariant features canbereused assymbols to build exponentially larger amounts of objects with higher complexity [1, 2, 3, 4].
Neural Information Processing Systems
Feb-11-2026, 22:48:25 GMT
- Technology: