Goto

Collaborating Authors

 tenenbaum


53d3f45797970d323bd8a0d379c525aa-Paper-Conference.pdf

Neural Information Processing Systems

To decouple the learning of underlying scene geometry from dynamic motion, we represent the scene as a time-invariantsigneddistance function (SDF)whichservesasareference frame, along with a time-conditioned deformation field.






UnsupervisedLearningofShapeandPose withDifferentiablePointClouds

Neural Information Processing Systems

We live in a three-dimensional world, and a proper understanding of its volumetric structure is crucial for acting and planning. However, we perceive the world mainly via its two-dimensional projections.


Bayesian Inference of Temporal Task Specifications from Demonstrations

Ankit Shah, Pritish Kamath, Julie A. Shah, Shen Li

Neural Information Processing Systems

Temporal logics have been used in prior research as a language forexpressing desirable system behaviors, and canimprovetheinterpretability ofspecifications if expressed as compositions of simpler templates (akin to those described by Dwyer et al. [2]).




Hamiltonian

Neural Information Processing Systems

See Appendix Aforanoteontrain/testsplitfor Task 3. loss Testloss Energy Baseline HNNBaseline HNNBaseline HNN mass-spring170 20.38 .1 pendulum 42 10 25 5 pendulum 390 7 14 5 (6.3e4 3e4 39 5 pendulum.3