Unified model bridges mechanistic and non-mechanistic epidemic approaches.
problem Understanding the dynamics of epidemics with flexibility and interpretability.
method A mixture-based model representing time series as Gaussian mixtures, derived from a networked SIR framework.
result The model provides interpretable parameters and low prediction error, validating its use in understanding interventions.
APD method decomposes neural network parameters into simple, faithful components.
problem Understanding the internal mechanisms learned by neural networks.
method Attribution-based Parameter Decomposition (APD) method.
result Demonstrated effectiveness in recovering features, separating computations, and identifying representations.
This paper tackles interpretability of LLMs in finance.
problem Complexity and lack of transparency of LLMs in finance.
method Mechanistic interpretability to understand LLM behavior.
result Demonstrates practical relevance of mechanistic interpretability in financial use cases.
Gradient descent optimization improved by circuit perspective.
problem Efficient training of large AI systems.
method Utilizing circuit perspective for mechanistic interpretability.
result Designing a curriculum for efficient learning.
Transformers learn topic structure through embedding and attention mechanisms.
problem Understanding how transformers capture semantic structure in text.
method Combination of mathematical analysis and experiments on Wikipedia and synthetic data.
result Embedding and attention layers encode topic structure in transformers.
Bilinear MLPs offer a new way to interpret deep learning models without complex nonlinearities.
problem Lack of mechanistic understanding in how MLPs compute.
method Introduced bilinear MLPs without element-wise nonlinearities, analyzed their weights using tensor and eigendecomposition.
result Bilinear MLPs provide interpretable weight structures and enable adversarial attacks and overfitting analysis.
Hybrid model improves forest growth predictions.
problem Misspecified assumptions in mechanistic models.
method Forest Informed Neural Networks (FINN) combining DVM and DNN.
result DNN learned improved growth process functional form.
Study forecasts cholera outbreaks in Malawi using dynamic models.
problem Cholera transmission forecasting in developing countries.
method Qualitative dynamics, Monte Carlo Markov Chain, sensitivity analysis, machine learning.
result Enhanced cholera forecasting models improve future trends prediction.
Unified understanding of neural networks on group operations verified.
problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.
Statistical models outperform mechanistic models in short-term COVID-19 incidence forecasts.
problem Comparing accuracy of mechanistic vs statistical models for short-term COVID-19 incidence forecasts.
method Empirical comparison of forecasts from mechanistic and statistical models using daily incidence data from six US states.
result Statistical models are at least as accurate as mechanistic models and better capture volatility.
New method sparsifies hybrid neural ODEs for better performance and stability.
problem Excessive latent states and interactions from mechanistic models lead to training inefficiency and over-fitting.
method Automatic state selection and structure optimization combining domain-informed graph modifications with data-driven regularization.
result Improved predictive performance and robustness with desired sparsity.
Paper develops efficient Bayesian inference for enzymatic SRNs with LNA metamodel.
problem Bayesian inference for nonlinear SDE-based mechanistic models with partial observations and measurement errors.
method Interpretable Bayesian updating LNA metamodel and efficient posterior sampling.
result Proposed approach demonstrates promising performance in empirical studies.
Bayesian approach for learning spatiotemporal systems from noisy data.
problem Efficiently modeling and learning from spatiotemporal dynamical systems with noisy data.
method Hierarchical state-space models with Gaussian process regression for efficient interpolation and training.
result Efficient modeling and learning of spatiotemporal dynamics using Bayesian methods.
Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we arg…
The paper argues for prioritizing identifying structure over complex models for scientific discovery.
problem Underdetermination of mechanisms in high-dimensional data, leading to unreliable explanations.
method Proposes concrete standards for 'mechanistic ML' to avoid collapsing explanations.
result Large language models (LLMs) can collapse large equivalence classes of explanations, making it hard to distinguish between mechanisms.
Unified framework for disentangled representations using mechanistic independence.
problem Identifiability of disentangled latent factors under statistical dependencies.
method Introduces mechanistic independence to characterize latent factors by their actions on observed variables, proposing various independence criteria.
result Establishes conditions for identifiability of latent subspaces without statistical assumptions.
Hybrid model learns interpretable meal-level glycemic control.
problem Lack of flexible, interpretable meal-level glycemic control methods.
method Hybrid variational autoencoder grounding latent space to mechanistic differential equation.
result Unsupervised representation discovers separation between individuals based on disease severity.
This paper introduces a new task to better understand Transformers in quantitative contexts.
problem Understanding Transformers in high-stakes quantitative and scientific applications.
method Introduces a novel contextual counting task and analyzes it with causal and non-causal Transformer architectures.
result Causal attention is better suited for the contextual counting task, and no positional embeddings lead to the best accuracy.
Hybrid models combine domain knowledge and data-driven learning for Earth observation.
problem Challenges in modelling Earth observation data with either purely mechanistic or data-driven methods.
method Gaussian process convolution models, specifically latent force models (LFMs), integrating physical knowledge into multioutput GP models.
result Model automatically estimates soil moisture persistence and discovers latent forces related to precipitation.
New methods for parameter estimation in mechanistic models using data-consistent inversion.
problem Parameter estimation bias in Bayesian analysis for mechanistic models.
method Data-consistent inversion methods based on rejection sampling, MCMC, GANs, and constrained optimization.
result Improved parameter estimation without bias from uninformative priors.
Breiman's data analysis dichotomy is outdated, offering a third approach: mechanistic models.
problem Data analysis dichotomy between data modelers and algorithmic modelers.
method Interpolating between simple interpretable models and flexible function approximations using mechanistic models.
result Flexible, interpretable, and scientifically-informed hybrids can provide accurate and robust predictions.
This work explains the structural origins of attention sinks in LLMs.
problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.
Triangulation filters spurious circuits in multilingual models.
problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.
Study detects and explains positional bias in financial LLMs.
problem Positional bias in financial decision-making using LLMs.
method Unified framework and benchmark for detecting and quantifying bias in Qwen2.5 models.
result Positional bias is pervasive, scale-sensitive, and resurfaces under nuanced prompt designs.
SGNNs use simulations to train neural networks, improving scientific forecasting and interpretability.
problem Combining precise theory and machine learning for robust scientific modeling.
method Pretraining neural networks on diverse mechanistic simulations as training data.
result SGNNs outperform data-driven and physics-constrained models in forecasting and interpretability.
Framework for imputing missing heart data to simulate brain-heart interactions.
problem Lack of multi-modal patient data representing heart and brain processes.
method Probabilistic framework for joint cardiac data imputation and mechanistic model personalization.
result Accurate imputation of missing cardiac features in incomplete datasets.
SAEs struggle with feature consistency across runs, hindering MI reliability.
problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.
Machine learning predicts COVID-19 activity in China.
problem Real-time forecasting of COVID-19 activity in Chinese provinces.
method Combines mechanistic disease models with digital traces (internet searches, news alerts). Uses clustering and data augmentation techniques.
result Stable and accurate forecasts 2 days ahead of current time, outperforming baseline models in 27 out of 32 provinces.
To understand how rich dynamics emerge in neural populations, we require models exhibiting a wide range of activity patterns while remaining interpretable in terms of connectivity and single-neuron dynamics. However, it has been challenging to fit such mechanistic spiking networks at the single neuron scale to empirica…
Physics-informed machine learning models improve biomolecular system simulations.
problem Modeling unresolved interactions beyond classical force fields.
method Physics-informed neural networks and operator learning.
result Accurate, mechanistic, generalizable models for long-timescale kinetics.
This research formalizes uncertainty quantification for Universal Differential Equations models.
problem Quantifying uncertainties in Universal Differential Equations models.
method Formalized uncertainty quantification methods for UDEs, including frequentist and Bayesian approaches.
result Evaluation of ensemble, variational inference, and MCMC sampling methods for UDEs.
Proposes counterfactual explainability for causal attribution, extending variance analysis methods.
problem Lack of mechanistic understanding in existing tools for explaining complex models.
method Extends global sensitivity analysis methods to causal explanations using directed acyclic graphs.
result Developed methods to estimate counterfactual explainability and applied to income inequality analysis.
Mechanistic models of single-neuron dynamics have been extensively studied in computational neuroscience. However, identifying which models can quantitatively reproduce empirically measured data has been challenging. We propose to overcome this limitation by using likelihood-free inference approaches (also known as App…
Capturing the microscopic interactions that determine molecular reactivity poses a challenge across the physical sciences. Even a basic understanding of the underlying reaction mechanisms can substantially accelerate materials and compound design, including the development of new catalysts or drugs. Given the difficult…
Study shows how specialized attention circuits emerge during transformer training.
problem Understanding the mechanisms of transformer training dynamics at large scales.
method Controlled sparse modular addition task; monitoring token evolution via visual sandbox.
result Specialized attention circuits (clustering heads) naturally emerge during training.
Purely data driven approaches for machine learning present difficulties when data is scarce relative to the complexity of the model or when the model is forced to extrapolate. On the other hand, purely mechanistic approaches need to identify and specify all the interactions in the problem at hand (which may not be feas…
Sharp limits found for storing and retrieving input-output associations in linear associative memories.
problem Understanding the fundamental limits of storing and retrieving input-output associations in neural networks.
method Study of a minimal linear associative memory model, introducing a decoupled model and using statistical physics to characterize storage capacity.
result Linear associative memory can store up to 1/2 log(p) associations, providing a sharp statistical-physics characterization.
Develops a new model to predict training dynamics of large language models.
problem Lack of mechanistic understanding of training dynamics in large language models.
method A first-principles reduced-order model of training dynamics, predicting group-size invariance and stability thresholds.
result Closed-form model predicts training dynamics with high accuracy and provides new diagnostics.
Biology has changed radically in the last two decades, transitioning from a descriptive science into a design science. Synthetic biology allows us to bioengineer cells to synthesize novel valuable molecules such as renewable biofuels or anticancer drugs. However, traditional synthetic biology approaches involve ad-hoc …
This paper explains how to optimize prompts for model adaptation.
problem Understanding and optimizing prompt tuning for model adaptation.
method Bayesian view and meta-learning to explain prompt optimization.
result Optimal prompting can be studied formally as conditioning Bayesian predictors.
The paper develops models to understand sensory coding and cortical topography.
problem Understanding how visual cortical areas' receptive fields and topographic maps relate to environmental statistical structure.
method Energy-based models applied to probability density estimation, constrained by biological constraints.
result The models qualitatively reproduce receptive field and map properties found in vivo.
Synthesizes computational approaches to understand neural timescales.
problem Varying definitions and measurements of neural timescales across studies.
method Reviews data analysis methods, biophysical models, and machine learning models.
result Complements experimental studies with a holistic view of neural timescales.
Study improves LLMs for PPI analysis by addressing uncertainty.
problem Uncertainty in LLM predictions for PPIs.
method Fine-tuned LLaMA-3 and BioMedGPT models, LoRA ensembles, Bayesian LoRA for UQ.
result Competitive PPI identification performance across diverse disease contexts.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
Adapts MBDOE for real-time parameter estimation in complex systems.
problem Costly posterior inference and design optimization in nonlinear systems.
method Combines DAD with differentiable mechanistic models for real-time parameter estimation.
result Demonstrated on four systems, including a DC motor.
New method uses Gaussian processes to improve PDE solver accuracy.
problem Uncertainty in PDE solver parameters and measurements.
method Physics-informed Gaussian process regression.
result Strictly generalizes weighted residual methods.
ISAAC audits deep models for drug-target interactions, revealing structural differences.
problem Deep models for DTI often use irrelevant features, making them hard to evaluate.
method ISAAC uses intervention-based structural auditing to evaluate model sensitivity.
result ISAAC reveals significant structural differences in DTI models' reasoning.
I present a unified discussion of several recently published results concerning the escalation, timing and severity of violent events in human conflicts and global terrorism, and set them in the wider context of real-world and cyber-based collective violence and illicit activity. I point out how the borders distinguish…