DSSM separates domain-invariant dynamics from domain-specifics in sequential data.
problem Learning cross-domain sequence representations from diverse data domains.
method Introduce disentangled state space models (DSSM) using unsupervised VAE-based training.
result Improves knowledge transfer and robust prediction across domains.
Study evaluates how much knowledge LLMs have by comparing their prediction accuracy to flexible models.
problem Evaluating the predictive power of LLMs without access to their training data.
method Equivalent sample size measure, comparing LLM's prediction error to flexible models trained on varying amounts of domain-specific data.
result LLMs encode varying amounts of predictive information across different economic variables.
Improves machine learning performance with domain-specific embeddings.
problem Tuning word embeddings for specific use cases and domains.
method Combines multiple domain-specific embeddings using a ranking function and dimensionality reduction.
result Effective domain-specific embeddings improve machine learning performance.
Framework improves CT image segmentation robustness with domain-specific cues.
problem Challenges in CT image segmentation by deep learning models.
method Combines domain-specific preprocessing and augmentation with CNN architectures.
result Framework stabilizes prediction performance on varying CT volumes.
Hybrid approach combines topic and graph embeddings for legal document clustering.
problem Challenges in classifying legal texts due to domain-specific language and limited labeled data.
method Combines unsupervised topic and graph embeddings with a supervised model.
result Improves clustering quality over text-only or graph-only embeddings.
Enhanced AI analysis predicts S&P 500 stock dynamics using various financial metrics.
problem Predicting S&P 500 stock performance with complex interplay of factors.
method Advanced financial metrics, machine learning, and integration of traditional and modern analytics.
result Enhanced predictive accuracy in market behavior and investment strategies.
A new model for imputing missing values in time series data across domains.
problem Imputing missing values in time series data across domains with domain shifts and high missing rates.
method A diffusion-based imputation model that integrates shared spectral components and domain-specific temporal structures, with cross-domain consistency alignment.
result Our model effectively handles missing values and domain shifts, outperforming existing methods.
CosML combines domain-specific meta-learners for cross-domain few-shot classification.
problem Generalizing to unseen domains while meta-learning on multiple seen domains.
method CosML trains domain-specific meta-learners and combines their meta-parameters in the parameter space.
result CosML outperforms state-of-the-art methods and achieves strong cross-domain generalization.
Study introduces KorFinMTEB for Korean financial texts, revealing model limitations.
problem Limited evaluation benchmarks for low-resource domains, especially Korean.
method Developed KorFinMTEB, a tailored benchmark for Korean financial texts.
result Models perform better on translated benchmarks than on domain-specific ones.
Method constructs finance LLMs without instruction data using pretraining and model merging.
problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.
Neural networks outperform conventional filters in inertial sensor-based attitude estimation.
problem Limited accuracy in inertial sensor-based attitude estimation due to dynamic and static motion.
method Investigated neural networks versus conventional filters for improving accuracy.
result Neural networks outperform conventional filters only with domain-specific optimizations.
The paper improves classification accuracy by leveraging a shared signal across domains in high-dimensional classification.
problem Improving classification accuracy in high-dimensional data with shared signals across domains.
method Transfer learning for linear discriminant analysis, decomposing mean differences into common and domain-specific components.
result Deterministic limits for transfer performance, leading to optimal weights and corrections for bias.
We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different, standard supervised learning methods perform poorly. Zero-shot domain adaptation attemp…
CSD learns a common component for domain generalization, outperforming existing methods.
problem Training models to generalize across unseen domains.
method CSD decomposes the model into a common and specific component, discarding the latter.
result CSD outperforms state-of-the-art domain generalization methods.
EQD model improves domain-specific QA by 0.6% to 10.5%.
problem Challenges in domain-specific quantitative reasoning for LLMs.
method Two-step fine-tuning framework guided by a reward function.
result EQD outperforms state-of-the-art models and prompting strategies.
Interventional domain adaptation improves feature transferability by removing spurious correlations.
problem Improper feature transferability due to spurious correlations in domain adaptation.
method Intervention strategy using unlabeled target data to generate counterfactual features and train discriminability invariance.
result Consistent performance improvements over state-of-the-art approaches in various domain adaptation tasks.
Generative model for set-valued data using permutation invariant flows.
problem Modeling set-valued data with conditional generative models.
method Conditional generative probabilistic model using continuous normalizing flows with permutation equivariant dynamics.
result Significantly outperforms non-permutation invariant baselines in log likelihood and domain-specific metrics.
Generative model identifies temporal count data components with regime-dependent contributions.
problem Modeling temporal count data with regime-dependent dynamics.
method Generative framework combining regime-adaptive dynamics with Poisson log-normal emissions.
result Established identifiability of the model and revealed co-variation patterns and regime shifts.
LLMs translate natural language trading intents into correct option strategies using a domain-specific language.
problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.
The paper tackles learning domain-specific bias by learning many tasks from the same domain.
problem Learning appropriate domain-specific bias in machine learning models.
method Learning many related tasks from the same domain, with a theorem bounding the number of tasks needed.
result The number of examples required per task for good generalization scales like \(O(a + \frac{b}{n})\), where \(O(a)\) is the minimum number of examples per task and \(O(a + b)\) is the number of examples per task independently.
Learn to automatically plug domain-specific modules into a common network.
problem Learning inflexibility and computational intensiveness in multi-domain learning.
method Neural Architecture Search (NAS) for data-driven adapter plugging and structure design.
result NAS-driven MDL model achieves comparable performance to existing approaches.
DDN dynamically combines weights for domain-specific models, improving performance.
problem Limited compute resources for edge devices.
method Domain-aware Dynamic Network (DDN) that combines specialized weights based on input domain.
result DDN achieves up to 2.6% higher AP50 than a static network on the BDD100K benchmark.
Study reveals XAI methods fail in neuroimaging, suggesting domain-specific adaptation.
problem Systematic failures of XAI methods in neuroimaging applications.
method Systematic comparison of XAI methods on 45,000 structural brain MRIs using a novel validation framework.
result Two widely used XAI methods (GradCAM and Layer-wise Relevance Propagation) fail to accurately explain neuroimaging data.
This paper introduces Sigma, a domain-specific computational representation for collaboration in large-scale for the field of economics. A computational representation is not a programming language or a software platform. A computational representation is a domain-specific representation system based on three specific …
Many complex systems exhibit extreme events far more often than expected for a normal distribution. This work examines how self-similar bursts of activity across several orders of magnitude can emerge from first principles in systems that adapt to information. Surprising connections are found between two apparently unr…
DACL tackles domain-specific contrastive learning by using Mixup noise.
problem Domain-specific contrastive learning methods rely on data augmentation techniques that require domain knowledge.
method DACL uses Mixup noise to create similar and dissimilar examples without domain-specific data augmentation.
result DACL outperforms other domain-agnostic noising methods and combines well with domain-specific methods.
EMFs combine deep learning and probabilistic models for better density estimation.
problem Combining domain-specific knowledge with general-purpose deep learning.
method Alternating transformations with structured layers that embed domain-specific inductive biases.
result EMFs induce desirable properties like multimodality and hierarchical coupling.
Protocol for constructing tailored evaluation datasets for semantic models.
problem Evaluation of domain-specific semantic models, focusing on top ranks.
method Adaptive pairwise comparisons, relatedness-based evaluation dataset, metrics, stochastic transitivity model.
result Effectiveness of the proposed dataset construction protocol confirmed.
New method transfers word embeddings from large to small datasets efficiently.
problem Challenges in learning word embeddings from new domains with limited data.
method Group-sparse matrix factorization for transfer learning.
result Efficiently learns domain-specific word embeddings with less data.
Solves Merton's investment-consumption problem with certainty equivalent approach.
problem Maximizing CRRA utility of consumption over time and investment mix.
method Identifies a certainty equivalent problem for the Merton problem, reformulates it as an SOCP, and applies it to model predictive control.
result The certainty equivalent problem can be solved as an SOCP, facilitating model predictive control.
Stock trend prediction is a challenging task due to the market's noise, and machine learning techniques have recently been successful in coping with this challenge. In this research, we create a novel framework for stock prediction, Dynamic Advisor-Based Ensemble (dynABE). dynABE explores domain-specific areas based on…
Method learns domain-specific representations without supervision.
problem Domain generalization without labeled data.
method Hierarchical variational autoencoder approach.
result Model generalizes to unseen domains without domain supervision.
Proposes a novel framework for unsupervised domain adaptation using specialized batch normalization.
problem Improves unsupervised domain adaptation in deep neural networks.
method Integrates domain-specific batch normalization layers in convolutional neural networks, estimating pseudo-labels for target domain examples and learning final models with multi-task classification loss.
result Achieves state-of-the-art accuracy in standard and multi-source domain adaptation scenarios.
Paper proposes a unified time series forecasting model with adaptive transfer.
problem General forecasting models for diverse time series data.
method Unified representations through Decomposed Frequency Learning and adaptive domain-specific features via Time Series Register.
result State-of-the-art forecasting performance on seven real-world benchmarks.
CausalLongPFN predicts counterfactual outcomes from time-series data.
problem Predicting future outcomes under varying treatments in time-series data with confounding and heterogeneity.
method Prior-fitted network pretrained on synthetic episodes of temporal structural causal models.
result CausalLongPFN outperforms domain-trained models on factual and counterfactual prediction tasks.
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
A new CNN architecture tackles domain shifts with a dictionary approach.
problem Handling domain shifts in deep learning models.
method Decompose CNN layers into domain-specific and shared parts using a dictionary of atoms.
result The approach promotes shared semantics across domains with minimal additional parameters.
The paper bounds Cheeger ratios of eigenfunctions and their level sets.
problem Understanding geometric features of Riemannian manifolds through eigenfunctions.
method Constructive upper bounds on Cheeger constants using eigenvalues and eigenfunctions.
result Upper bounds on Cheeger ratios of eigenfunction level sets and their superlevel sets.
The study questions the necessity of accurate models in MBRL.
problem The difficulty of achieving and utilizing accurate models in complex or changing environments.
method Introduces a meta-learning algorithm focused on model usefulness rather than accuracy.
result Meta-learning models enable faster learning than accurate models built with domain-specific knowledge.
The wide adoption of DNNs has given birth to unrelenting computing requirements, forcing datacenter operators to adopt domain-specific accelerators to train them. These accelerators typically employ densely packed full precision floating-point arithmetic to maximize performance per area. Ongoing research efforts seek t…
Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions t…
Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium imaging (CaI) of different organisms (zebrafish and rat), aiming to build a model of joint activation dynamics in large neuronal populations, including the whole brain of zebra…
This paper examines inductive biases in deep reinforcement learning and their impact on performance.
problem The trade-off between inductive biases and performance in deep reinforcement learning.
method Investigated domain-specific components and adaptive solutions in deep reinforcement learning agents.
result Adaptive components can sometimes outperform domain-specific components, but not always.
Ontology learning is a critical task in industry, dealing with identifying and extracting concepts captured in text data such that these concepts can be used in different tasks, e.g. information retrieval. Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatica…
By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carl…
URT layer improves few-shot image classification across diverse domains.
problem Few-shot image classification in multi-domain settings.
method Meta-learns to dynamically re-weight and compose domain-specific representations.
result Sets new state-of-the-art on Meta-Dataset.
DASH simplifies neural networks for gene regulatory dynamics using domain knowledge.
problem Pruning neural networks for gene regulatory dynamics lacks biologically meaningful structure learning.
method DASH uses domain-specific structural information to guide network pruning, leading to sparser, better interpretable models.
result DASH outperforms general pruning methods in gene regulatory network inference, yielding deeper insights.
BondBERT improves sentiment analysis for bond markets.
problem Misleading sentiment models for bond markets due to domain-specific dynamics.
method Fine-tuned transformer model on bond-specific news.
result BondBERT produces positive correlations with bond returns and higher forecasting accuracy.