3 papers
cs.LG2026
LexiCan: Lexicographic Canonicalization of Point Clouds for Machine Learning Applications
Daniel Sanchez, Djordje Mihajlovic, Federica Valeau +4
Canonicalization resolves the rotational and permutation ambiguity of 3D point clouds by selecting a unique orbit representative, maintaining their geometric information while allo…
cs.LG2026
Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning
Soutrik Sarangi, Yonatan Sverdlov, Adir Dayan +2
Learning properties of neural networks has recently attracted growing interest, with existing approaches operating either directly on network parameters or through probe-based repr…
cs.LG2025
Monotone and Separable Set Functions: Characterizations and Neural Models
Soutrik Sarangi, Yonatan Sverdlov, Nadav Dym +1
Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on se…