Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
hub Canonical reference
Representation Learning: A Review and New Perspectives
Canonical reference. 80% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
80% of classified citations
abstract
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, auto-encoders, manifold learning, and deep networks. This motivates longer-term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation and manifold learning.
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
verdicts
UNVERDICTED 12representative citing papers
RNN computation is recovered from multi-hop graph pathways, and constraining these pathways via resolvent regularization yields improved temporal sparsity and task performance over standard L1.
Sparse autoencoders scaled to 34 million features on Claude 3 Sonnet yield interpretable, steerable representations of concrete and abstract concepts that generalize across languages and modalities.
Success bias in collective theory-building leads to systematic overestimation of theory quality, narrower search, and paradoxically lower performance when agents optimize for apparent success.
The paper frames Cayley-table completion as the discrete algebraic analog to matrix completion and poses the open problem of proving exact recovery bounds under flatness priors that favor associativity.
CLEAR-HPV restructures the latent space of attention-based MIL models to discover 10 label-free morphologic concepts that preserve slide-level HPV prediction performance and generalize across TCGA-HNSCC, TCGA-CESC, and CPTAC-HNSCC datasets.
Landmark topological coverings derived from traversibility metrics enable three transfer mechanisms with theoretical Q-value bounds in goal-based multi-task lifelong RL.
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
Supervised and reinforcement learning are used to find initial adjoint variables for real-time solution of Hamilton-Jacobi-Bellman equations in two-point boundary value problems.
Proposes possibility space, timing computation, and causal factum as a new framework for data-driven trajectory discovery and counterfactual timing deduction on EHR data from 3,276 breast cancer patients.
A survey providing an overview of publicly available image-based datasets for ML/DL-based disaster management pipelines covering pre-disaster, during, and post-disaster phases.
Presents a generalized mathematical operator framework that defines conflict as an independent, context-sensitive object integrating weighting, scale, and mapping components.
citing papers explorer
-
Generative models on phase space
Generative diffusion and flow models are constructed to remain exactly on the Lorentz-invariant massless N-particle phase space manifold during sampling for particle physics applications.
-
Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks
RNN computation is recovered from multi-hop graph pathways, and constraining these pathways via resolvent regularization yields improved temporal sparsity and task performance over standard L1.
-
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Sparse autoencoders scaled to 34 million features on Claude 3 Sonnet yield interpretable, steerable representations of concrete and abstract concepts that generalize across languages and modalities.
-
Nothing Deceives Like Success: Social Learning and the Illusion of Understanding in Science
Success bias in collective theory-building leads to systematic overestimation of theory quality, narrower search, and paradoxically lower performance when agents optimize for apparent success.
-
Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion
The paper frames Cayley-table completion as the discrete algebraic analog to matrix completion and poses the open problem of proving exact recovery bounds under flatness priors that favor associativity.
-
CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology
CLEAR-HPV restructures the latent space of attention-based MIL models to discover 10 label-free morphologic concepts that preserve slide-level HPV prediction performance and generalize across TCGA-HNSCC, TCGA-CESC, and CPTAC-HNSCC datasets.
-
On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning
Landmark topological coverings derived from traversibility metrics enable three transfer mechanisms with theoretical Q-value bounds in goal-based multi-task lifelong RL.
-
Computational Hermeneutics: Evaluating generative AI as a cultural technology
Generative AI should be evaluated through computational hermeneutics using iterative, human-inclusive benchmarks that measure cultural context rather than isolated model outputs.
-
Learning-based Hamilton-Jacobi-Bellman Methods for Optimal Control
Supervised and reinforcement learning are used to find initial adjoint variables for real-time solution of Hamilton-Jacobi-Bellman equations in two-point boundary value problems.
-
To Use AI as Dice of Possibilities with Timing Computation
Proposes possibility space, timing computation, and causal factum as a new framework for data-driven trajectory discovery and counterfactual timing deduction on EHR data from 3,276 breast cancer patients.
-
Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications
A survey providing an overview of publicly available image-based datasets for ML/DL-based disaster management pipelines covering pre-disaster, during, and post-disaster phases.
-
A Mathematical Conflict Framework for Contextual Data Modulation
Presents a generalized mathematical operator framework that defines conflict as an independent, context-sensitive object integrating weighting, scale, and mapping components.