EAGLE-Net enhances foundation models by integrating patch-level features for better tissue understanding.
problem Foundation models lack mechanisms for global tissue structure and local context in computational pathology.
method EAGLE-Net combines multi-scale spatial encoding, attention-guided loss functions, and background suppression to aggregate patch-level features into slide-level predictions.
result EAGLE-Net improves classification accuracy and concordance indices across multiple cancer types, producing biologically coherent attention maps.
GAMformer bridges tabular models and interpretability, offering a single-pass approach.
problem Lack of interpretability in tabular foundation models like TabPFN.
method In-context learning for GAM shape functions, training on synthetic data.
result GAMformer performs comparably to other leading GAMs across various classification benchmarks.
Introduces foundation priors for using model-generated data in empirical research.
problem Using model-generated data as real observations in empirical research.
method Introduces foundation priors as an exponential-tilted, generalized Bayesian update of the user's primitive prior.
result Synthetic data reflects both model patterns and user's priors, enabling principled use in empirical work.
New definition of interpretability makes model design more actionable.
problem Current definitions of interpretability are not actionable and inform users poorly.
method Proposes a new definition of interpretability that is general, simple, and actionable.
result New definition reveals necessary properties for designing interpretable models.
Paper presents a copula-based method to efficiently generate correlated sample paths from multi-step time series models.
problem Generating realistic correlation structures in multi-step forecast sample paths is expensive and time-consuming.
method Copula-based approach to generate correlated sample paths in one forward pass.
result Improved sample path quality and significant speedup over autoregressive sampling.
Framework fine-tunes foundation models with semi-supervised learning for downstream tasks and latent spaces.
problem Training foundation models with limited labelled data.
method Mutual information decomposition for downstream and latent spaces, semi-supervised fine-tuning.
result Significant improvements in classification tasks under low-labelled conditions.
Intro to Poisson geometry, focusing on basics and recent tools.
problem Understanding Poisson structures and their applications.
method Exercises leading to conclusions on foundational and recent topics.
result Introduction to Poisson geometry basics and recent developments.
Foundation models outperform supervised methods in time series forecasting across various operational regimes.
problem Lack of domain-specific training and ongoing maintenance in supervised learning for time series forecasting.
method Evaluation of foundation models against standard supervised approaches across four operational regimes: periodic, physically constrained, stochastic, and demand forecasting.
result Foundation models are optimal for cold-start or long-tail scenarios and perform well in domains with transferable periodic structures.
FEET protocol evaluates foundation models across three scenarios.
problem Lack of standardized evaluation protocols for foundation models.
method Structured evaluation protocol across three use cases: frozen, few-shot, and fine-tuned embeddings.
result Demonstrates comprehensive assessment of foundation models' effectiveness.
Survey on geometric foundations of data reduction methods.
problem High-dimensional data with intrinsic nonlinear structure.
method Spectral manifold learning methods.
result Derivation and convergence analysis of spectral manifold learning.
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
New framework explains leading digit patterns without probabilistic assumptions.
problem Explaining leading digit distributions without relying on probabilistic models.
method Shift-invariant functional equation and affine-plus-periodic formulas.
result Unified mathematical foundation for understanding digit distributions.
VMoER improves uncertainty quantification in MoE layers for scalable foundation models.
problem Uncertainty quantification in large-scale models like MoE layers.
method Structured Bayesian approach with amortized variational inference over routing logits and temperature parameter inference.
result Improves routing stability, reduces calibration error, and increases AUROC by 12%.
The paper explores theories behind graph and relational data vector embeddings.
problem Understanding the foundations of vector embeddings for graphs and relational structures.
method Proposes two theoretical approaches to understand vector embeddings.
result Draws connections between various embedding techniques and suggests future research directions.
Foundations of derived geometry in smooth settings.
problem Building tools for moduli spaces in differential geometry.
method Abstract structured spaces and universal properties in (∞,2)-categories. result Established derived flatness results for derived C∞-rings. Flexible Kernels for Protein Property Prediction
problem Predicting protein properties from sparse experimental data
method Sequence kernels using evolutionary substitution matrices and local linearity
result Data-efficient models of protein property landscapes
This paper organizes recent deep learning theory advances.
problem Lack of theoretical foundations in deep learning.
method Literature review and categorization into six groups.
result Organized recent advances in deep learning theory.
InfoAtlas speeds up MI estimation for real-time data analysis.
problem Efficiently measuring statistical dependency between high-dimensional datasets.
method Directly infers mutual information in a single forward pass using a pretrained model.
result Matches state-of-the-art accuracy with 100x speedup.
Foundation models struggle with multi-turn exploration but can learn through regular summaries.
problem Foundation models struggle with multi-turn exploration in dynamic environments.
method Implemented a text-based version of the Alchemy environment to test multi-trial learning. Prompting models to summarize their observations at regular intervals enabled them to improve across trials and adapt to changes.
result Foundation models can improve through regular summaries, enabling multi-trial learning and adaptation.
Prior to the financial crisis mortgage securitization models increased in sophistication as did products built to insure against losses. Layers of complexity formed upon a foundation that could not support it and as the foundation crumbled the housing market followed. That foundation was the Gaussian copula which faile…
Localized Multidirectional Correction improves non-refusal target-response behavior in foundation models.
problem Controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models.
method Introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework.
result Substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.
Study on G2-structures manifold geometry.
problem Understanding the space of closed G2-structures. method Developed Sobolev-type metrics, Levi-Civita connections, geodesic equations.
result Formulated variational structures of torsion-free G2-structures. New algebra counts components of arborescent knots and links.
problem Counting components of arborescent knots and links.
method Developed a new algebra called the crossing algebra.
result The crossing algebra counts the number of components for arborescent knots and links.
ML reduces high-dimensional data to reveal its underlying structure.
problem Handling large, high-dimensional data sets.
method Non-linear dimension reduction techniques.
result Reveals the geometric shape of high-dimensional data.
Research reveals deep networks often learn low-rank structures, leading to more efficient training and fine-tuning.
problem Efficient training and deployment of large-scale deep learning models.
method Complementary theoretical perspectives on low-rank structures during training and convergence, and practical applications of LoRA and masked training.
result Understanding and exploiting low-rank structures can improve efficiency and effectiveness of training and fine-tuning.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.
Lecture notes on reinforcement learning using statistical methods.
problem Addressing the exploration-exploitation dilemma in decision making.
method Frequentist and Bayesian approaches, function approximation, neural networks.
result Unified framework for decision making and estimation.
CDFM aims to unify causal discovery across diverse datasets.
problem Fragmented, test-driven causal discovery approaches struggle with modern data heterogeneity.
method CDFM is a unified, general-purpose framework using a variational decomposition of causal mechanisms.
result CDFM outperforms traditional algorithms across diverse datasets.
BLAST optimizes deep model inference by learning efficient matrix structures.
problem Efficient inference of large-scale deep neural networks.
method Introduces BLAST matrix for adaptive structured weights.
result Significant compression and performance improvements for various model sizes.
Develops SCMs for latent selection to simplify causal analysis.
problem Latent selection complicates causal analysis.
method Introduces a conditioning operation for SCMs to encode latent selection.
result Conditioning operation preserves simplicity, acyclicity, and linearity of SCMs.
Orion-Bix combines biaxial attention and meta-learning for tabular few-shot learning.
problem Scaling and generalizing tabular models with mixed numeric and categorical fields, weak feature structure, and limited labeled data.
method Orion-Bix uses biaxial attention and meta-learned in-context reasoning to efficiently capture local and global dependencies.
result Orion-Bix outperforms gradient-boosting baselines and state-of-the-art tabular models on public benchmarks.
STOIC improves energy demand forecasting with reliable uncertainty estimates.
problem Accurate point forecasts alone are insufficient for energy systems; reliable uncertainty estimates are needed.
method Integrates graph-based forecasting with tabular foundation models for zero-shot calibration of spatial-temporal residuals.
result STOIC delivers more reliable and robust uncertainty estimates for complex graph-structured energy time series.
Defines Learning Analytics' foundational structure and scope.
problem Lack of theoretical foundation in Learning Analytics.
method Proposes an axiomatic theory based on psychological learning and LA methodology.
result Clarifies the epistemological stance of Learning Analytics and its limitations.
Develops a logifold structure for understanding datasets.
problem Understanding and classifying complex datasets.
method Local-to-global approach using measure-theoretical models.
result Improves accuracy in data classification problems.
Survey of financial foundation models for diverse applications.
problem Challenges in applying general-purpose FMs to financial tasks.
method Review of financial foundation models (FFMs) in three modalities.
result Emergence of FFMs designed specifically for finance.
Revises Bayesian model averaging for foundation models.
problem Ensemble pre-trained and lightly-finetuned foundation models for improved classification performance.
method Introduces trainable linear classifiers and computationally cheaper model averaging scheme (OMA).
result Ensembled models can better predict on various datasets.
Time series foundation models are well-calibrated, improving over baseline models.
problem Calibration of time series foundation models for practical applications.
method Systematic evaluations of five time series foundation models and two baselines, assessing calibration, prediction heads, and long-term forecasting.
result Time series foundation models are consistently better calibrated than baseline models and do not show over- or under-confidence.
Combines foundation models with weak supervision to improve NLP and video tasks.
problem Leveraging weak supervision with foundation models without labeled data.
method Liger, a combination of foundation model embeddings and weak supervision techniques.
result Liger outperforms existing weak supervision methods by 14.1 points on benchmark NLP and video tasks.
Foundation models trained on collider data improve jet generation tasks.
problem Improving foundation models for jet generation tasks.
method Pre-training OmniJet-α model on AspenOpenJets dataset. result Pre-trained model improves performance on jet generation tasks with domain shift.
DisCoPyro combines category theory with machine learning for program learning.
problem Applying category theory to machine learning tasks.
method Introducing DisCoPyro, a framework combining categorical structures with amortized variational inference.
result DisCoPyro can be applied in program learning for variational autoencoders and potentially contributes to AGI.
New measure assesses time series pre-training data quality without labels.
problem Challenges in collecting diverse pre-training datasets for time series classification.
method Contrastive-learning-based foundation model and contrastive accuracy measure.
result Contrastive accuracy correlates with model performance on downstream tasks.
Revisits Finsler spacetimes from inertial observer perspective.
problem Physical foundations of relativistic spacetimes.
method Inertial observers and double linear approximation.
result Finsler spacetimes are defined by dropping the second linearization.
In the framework of nonassociative geometry (hep-th/0003238) a unified description of continuum and discrete spacetime is proposed. In our approach at the Planck scales the spacetime is described as a so-called "diodular discrete structure" which at large spacetime scales `looks like' a differentiable manifold. After a…
Paper explores foundation models for dynamical systems using synthetic data.
problem Lack of synthetic data for dynamical systems training.
method Pretrained transformer model on synthetic dynamics functions sampled from RKHS.
result Pretrained model generalizes across various dynamical systems in simulations and hardware.
Paper speeds up large foundation models for time series data.
problem Resource-intensive foundation models limit accessibility.
method Dimensionality reduction techniques, including PCA and neural network adapters.
result Up to 10x speedup and 4.5x more datasets fit on a single GPU.
Deep generative model discovers inhibitors for unknown targets.
problem Discovering novel inhibitor molecules for unknown drug targets.
method Deep generative framework trained on protein sequences, small molecules, and interactions.
result Micromolar-level inhibition observed for two out of four synthesized candidates, including activity against SARS-CoV-2 variants.
The natural habitat of most Bayesian methods is data represented by exchangeable sequences of observations, for which de Finetti's theorem provides the theoretical foundation. Dirichlet process clustering, Gaussian process regression, and many other parametric and nonparametric Bayesian models fall within the remit of …