arXiv:2503. 13051v3 Announce Type: replace Abstract: Sorting and permutation learning are key concepts in optimization and machine learning, especially when organizing high-dimensional data into meaningful spatial layouts.
By Kai Uwe Barthel, Florian Barthel, Peter Eisert
arXiv:2608.23400v1 Announce Type: cross
Abstract: Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via ite...
By Jiaqi Wang, Tianying Liu, Heng Chang, Jihong Guan, Wengen Li, Shuigeng Zhou
arXiv:2602. 11453v2 Announce Type: replace-cross Abstract: In information retrieval (IR), learning-to-rank (LTR) methods have traditionally limited themselves to discriminative machine learning approaches that model the probability of the document being relevant to the query given some feature representation of the query-document pair.
By Sajad Ebrahimi, Bhaskar Mitra, Negar Arabzadeh, Ye Yuan, Haolun Wu, Fattane Zarrinkalam, Ebrahim Bagheri
arXiv:2607. 10951v1 Announce Type: new Abstract: We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings.
By Pascal Jutras-Dub\'e, Patrick Pynadath, Jeremy Lu, Yuan Gao, Ruqi Zhang
arXiv:2606. 00295v1 Announce Type: new Abstract: Masked diffusion models have seen great success in capturing data distributions over discrete sequences in domains such as text and proteins.
By Jama Hussein Mohamud, Mohsin Hasan, Mirco Ravanelli, Yoshua Bengio
We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings. In forward time, anchors release their mass at a hazard rate and the released mass diffuses in the continuous ambient space; time reversal couples a score-driven SDE with a sticky jump kernel whose rate and destination are fixed by flux balance with the forward law.