_id,title
14106,Are two heads the same as one? Identifying disparate treatment in fair neural networks
14107,Self-supervised amodal video object segmentation
14114,Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers
14168,Neural attentive circuits
14170,Generalization and robustness implications in object-centric learning
14171,Score matching enables causal discovery of nonlinear additive noise  models
14172,Visual representation learning does not generalize strongly within the  same domain
14173,Assaying out-of-distribution generalization in transfer learning
14174,The role of pretrained representations for the OOD generalization of  reinforcement learning agents
14175,You mostly walk alone: Analyzing feature attribution in trajectory prediction
14215,A general purpose neural architecture for geospatial systems
14216,ASIF: Coupled data turns unimodal models to multimodal without training
14220,Compositional multi-object reinforcement learning with linear relation networks
9199,Equidistribution and freeness on Grassmannians
9311,Finite-memory strategies in POMDPs with long-run average objectives
9364,On the size of the maximum of incomplete Kloosterman sums
9649,The topological correctness of PL approximations of isomanifolds
10016,Fourteen stations of auxin
10018,Integral points on singular del Pezzo surfaces
10042,Defect engineering in solution-processed polycrystalline SnSe leads to high thermoelectric performance