Hypernetworks distill modular reservoir connectivity via a genomic bottleneck to generate sparse recurrent networks solving difficult temporal tasks with minimal training and maintained robustness.
International conference on learning representations , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
method 2polarities
use method 2representative citing papers
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
A fair conformal classification method guarantees conditional coverage on adaptively identified subgroups defined via learned representations.
WorldComp2D explicitly structures latent space geometry by object identity and spatial proximity via a proximity-dependent encoder and localizer, cutting parameters up to 4X and FLOPs 2.2X versus state-of-the-art lightweight models on facial landmark localization while staying real-time on CPU.
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.
citing papers explorer
-
Distilling a Modular Reservoir Through a Genomic Bottleneck
Hypernetworks distill modular reservoir connectivity via a genomic bottleneck to generate sparse recurrent networks solving difficult temporal tasks with minimal training and maintained robustness.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
What Makes a Representation Good for Single-Cell Perturbation Prediction?
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
-
Fair Conformal Classification via Learning Representation-Based Groups
A fair conformal classification method guarantees conditional coverage on adaptively identified subgroups defined via learned representations.
-
WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
WorldComp2D explicitly structures latent space geometry by object identity and spatial proximity via a proximity-dependent encoder and localizer, cutting parameters up to 4X and FLOPs 2.2X versus state-of-the-art lightweight models on facial landmark localization while staying real-time on CPU.
-
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.