A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
hub Mixed citations
Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324
Mixed citation behavior. Most common role is background (40%).
13
Pith papers citing it
Background
40% of classified citations
hub tools
citation-role summary
background 2
dataset 1
method 1
other 1
citation-polarity summary
representative citing papers
Subliminal learning occurs via compatible auxiliary and class output heads on task-unrelated inputs, even with random hidden layers or architecture changes, with theory and upper bounds on failure.
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
DR-IS selects low-contamination subsets via bounded rank-disagreement in proxy ensembles under an ε-contamination model, with O(√(log(N/δ)/K)) concentration rates that certify separation when the expectation gap Δ' is positive.
Defines diffusion processes on implicit data manifolds via proximity-graph approximations to the infinitesimal generator and carré-du-champ operator, proves convergence in law to the continuous manifold process, and provides an Euler-Maruyama integrator validated on synthetic and MNIST manifolds.
CogAlpha combines LLM reasoning with code-level evolutionary search to discover financial alphas that show higher predictive accuracy and generalization than prior methods on five stock datasets.
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
COCOCO is a conformal framework for NeSy-CBMs that jointly conformalizes concepts and labels, reconciles them via deduction-abduction revision, and satisfies consistency, coverage, and conciseness while retaining distribution-free guarantees.
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
Drift Flow Matching connects direct transport maps from Drift Models with flow-based iterative refinement to enable adaptive computation in generative modeling.
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.
citing papers explorer
-
Any-Dimensional Invariant Universality
A systematic approach maps any-dimensional invariant functions to a unique function on an infinite-dimensional limit space admitting a topology with compact sets where universality holds, with examples of non-universal architectures and fixes.
-
Learning Through Noise: Why Subliminal Learning Works and When It Fails
Subliminal learning occurs via compatible auxiliary and class output heads on task-unrelated inputs, even with random hidden layers or architecture changes, with theory and upper bounds on failure.
-
Discrete Langevin-Inspired Posterior Sampling
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
-
How Much is Brain Data Worth for Machine Learning?
Brain data is worth a variable number of task samples depending on task-brain alignment, noise levels, and latent dimension, with conditions under which it also improves robustness to test distribution shift.
-
Disagreement-Regularized Importance Sampling for Adversarial Label Corruption
DR-IS selects low-contamination subsets via bounded rank-disagreement in proxy ensembles under an ε-contamination model, with O(√(log(N/δ)/K)) concentration rates that certify separation when the expectation gap Δ' is positive.
-
Diffusion Processes on Implicit Manifolds
Defines diffusion processes on implicit data manifolds via proximity-graph approximations to the infinitesimal generator and carré-du-champ operator, proves convergence in law to the continuous manifold process, and provides an Euler-Maruyama integrator validated on synthetic and MNIST manifolds.
-
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
CogAlpha combines LLM reasoning with code-level evolutionary search to discover financial alphas that show higher predictive accuracy and generalization than prior methods on five stock datasets.
-
Generative Recursive Reasoning
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
-
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
COCOCO is a conformal framework for NeSy-CBMs that jointly conformalizes concepts and labels, reconciles them via deduction-abduction revision, and satisfies consistency, coverage, and conciseness while retaining distribution-free guarantees.
-
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
-
UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
-
Drift Flow Matching
Drift Flow Matching connects direct transport maps from Drift Models with flow-based iterative refinement to enable adaptive computation in generative modeling.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.