Function graph transformers use graph measures to provide a measure-theoretic framework where standard transformer components universally approximate operators between function spaces while preserving single-valued function outputs.
International Conference on Learning Representations , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
ASAP amortizes Sinkhorn-based doubly-stochastic attention by learning a parametric map from 1D potentials to the Sinkhorn dual and reconstructing the plan via two-sided entropic c-transform, delivering 5.3x faster inference at matched accuracy.
FRACTAL integrates fractional recurrent architecture into SSMs using a tunable singularity index to capture multi-scale temporal features, reporting 87.11% average on Long Range Arena and outperforming S5.
Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
S5 uses a single MIMO state space model with S4-derived initialization to match S4 efficiency and reach 87.4% average accuracy on the Long Range Arena benchmark.
LaplacianFormer uses a Laplacian kernel with an injective feature map and efficient approximations to achieve linear attention that preserves mid-range interactions better than Gaussian-based linear attention in vision transformers.
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.
citing papers explorer
-
Function graph transformers universally approximate operators between function spaces
Function graph transformers use graph measures to provide a measure-theoretic framework where standard transformer components universally approximate operators between function spaces while preserving single-valued function outputs.
-
Convergent Stochastic Training of Attention and Understanding LoRA
Attention and LoRA regression losses induce Poincaré inequalities under mild regularization, so SGD-mimicking SDEs converge to minimizers with no assumptions on data or model size.
-
ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection
ASAP amortizes Sinkhorn-based doubly-stochastic attention by learning a parametric map from 1D potentials to the Sinkhorn dual and reconstructing the plan via two-sided entropic c-transform, delivering 5.3x faster inference at matched accuracy.
-
FRACTAL: SSM with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
FRACTAL integrates fractional recurrent architecture into SSMs using a tunable singularity index to capture multi-scale temporal features, reporting 87.11% average on Long Range Arena and outperforming S5.
-
Towards Understanding Self-Pretraining for Sequence Classification
Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.
-
Simplified State Space Layers for Sequence Modeling
S5 uses a single MIMO state space model with S4-derived initialization to match S4 efficiency and reach 87.4% average accuracy on the Long Range Arena benchmark.
-
LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
LaplacianFormer uses a Laplacian kernel with an injective feature map and efficient approximations to achieve linear attention that preserves mid-range interactions better than Gaussian-based linear attention in vision transformers.
-
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.