Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
Kaiwen Bian, Andrew H. Yang, Yusu Wang +2
Autoregressive graph generators typically linearize graphs through flat node-edge walks, which can obscure higher-order structure in large and complex graphs. We introduce a hierar…
cs.LG2026
Shaped by What's Missing: Topological Invariance Simplification Discovers Behavioral Transitions
Kaiwen Bian, Eric J. Leonardis, Yuanjia Yang +3
Understanding how animals move between behaviors is a central question in neuroethology, yet most segmentation methods first partition time into discrete states, leaving transition…