other

Operator Learning

otheractiveprovisionaloperator-learning-88ec59ac·1 events·first seen 16d ago

Aliases: Operator Learning

Co-occurring entities

Transformers Functional Attention Functional Maps

More like this (12)

Learning with Opponent-Learning Awareness (LOLA)Multi-Task Learning Imitation Learning self-training Language Modeling Loss ExpRL: Exploratory RL for LLM Mid-Training Class-Incremental Learning Multimodal Learning Soft Q-Learning KL-regularized RL Q-learning Alternating Token-Weighted Unlearning

Recent events (1)

5arXiv · cs.LG·16d ago·source ↗

Functional Attention: Reinterpreting Attention as Functional Correspondences for Operator Learning

This paper introduces Functional Attention, a novel attention mechanism for operator learning that replaces standard softmax token-wise affinities with structured linear operators inspired by geometric functional maps. The approach treats attention as a correspondence between adaptive bases rather than discrete tokens, yielding a resolution-invariant, globally-aware representation. Experiments show competitive or state-of-the-art performance on PDE solving, 3D segmentation, and regression tasks, with robustness to varying discretizations.

Long Context Evolution Transformers Functional Attention Operator Learning +1 more