archive
Every paper Pith has read. Search by title, abstract, or pith.
506 papers in cs.CE · page 10
-
Curriculum model generalizes nanomaterial-protein predictions to new cases
Curriculum-guided multimodal representation learning enables generalizable prediction of nanomaterial-protein interactions
-
SysML diagrams turn text into dynamical system models
Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams
-
Agency adds goal-directed social smarts to autonomous vehicles
Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy
-
Horse plowing shift allowed suppressing resistance while empowering people
The gradual transformation of inland areas -- human plowing, horse plowing and equity incentives
-
Multimodal RAG outperforms ChatGPT-4o by 19 points on financial QA
MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
-
Neural functional surpasses hybrid DFT at semi-local cost
Accurate and scalable exchange-correlation with deep learning
-
Bounding box methods speed shared charging schedules
Collaborative Charging Scheduling via Balanced Bounding Box Methods
-
LLMs cut feedback loops in design matrices
Large Language Models for Combinatorial Optimization of Design Structure Matrix
-
Masking non-tradable prices lifts A-share trading Sharpe by 0.44
Machine Learning Enhanced Multi-Factor Quantitative Trading: A Cross-Sectional Portfolio Optimization Approach with Bias Correction
-
LLMs extract financial numbers but fail at US GAAP concept links
FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
-
New dataset labels 51,500 satellite images with 14 roof types
RoofNet: A Global Multimodal Dataset for Roof Material Identification from Earth Observation
-
High-order DG handles irregular bathymetry in shallow water flows
High-order adaptive discontinuous finite elements for the shallow water equations with sub-grid irregular bathymetry
-
Weight-space diffusion adapts dynamics predictors to shifts
Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion
-
Latent generative model samples random fields from limited data
Latent Generative Modeling of Random Fields from Limited Training Data
-
Bayesian analysis values strain monitoring for ship corrosion
Value of Information-based assessment of strain-based thickness loss monitoring in ship hull structures
-
8-bit voltage data recovers grid topologies
Information-Theoretic Grid Topology Reconstruction using Low-Precision Smart Meter Data
-
Unsupervised network extracts modal properties across structures
Modal Decomposition and Identification for a Population of Structures Using Physics-Informed Graph Neural Networks and Transformers
-
Digital twin fuses knowledge graphs and ensemble learning for patient care
Design for a Digital Twin in Clinical Patient Care
-
Compositional framework analyzes blockchain incentive compatibility
A Composable Game-Theoretic Framework for Blockchains
-
H-conforming foil-winding models match resolved meshes at lower cost
Magnetic Field Conforming Formulations for Foil Windings
-
Modeling compounds as treatments boosts microscopy reps
Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling
-
Prior knowledge graphs lift drug response AUC to 0.894 in GraphPINE
GraphPINE: Graph Importance Propagation for Interpretable Drug Response Prediction
-
Multi-level bond sentiment cuts credit spread errors by 10%
MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market
-
LLMs retrieve novel inspirations across 12 research fields
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
-
Fourier operator predicts grain growth at any grid size
Teaching Artificial Intelligence to Perform Rapid, Resolution-Invariant Grain Growth Modeling via Fourier Neural Operator
-
xLSTM-PPO trading agent beats LSTM on returns and Sharpe ratio
A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networks
-
Algae bricks enable user-built GHG-reducing building facades
Modular Photobioreactor Facade Systems for Sustainable Architecture -- A case study
-
Deep learning cuts covariance forecast error by 20% vs benchmarks
A Deep Learning Framework for Medium-Term Covariance Forecasting in Multi-Asset Portfolios
-
Benchmark splits stock patterns into four types and adds real trading fees
FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting
-
CausalGANs plus RL cut bond yield error to 0.103 MAE
Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation
-
Differentiable solver inverts Manning's n and learns generalizable roughness
Scientific Machine Learning of Flow Resistance Using Universal Shallow Water Equations with Differentiable Programming
-
Convex networks achieve universal approximation for polyconvex energies
Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
-
Deep BSDE converges beyond Lipschitz generators
XNet-Enhanced Deep BSDE Method and Numerical Analysis
-
VAEs match physics models predicting SUV jerk from torque
Drivetrain simulation using variational autoencoders
-
Air-gap element enables space-time simulation of electric machines
An Air-Gap Element for the Isogeometric Space-Time-Simulation of Electric Machines
-
Assembly-like FEM updating cuts effort 28% with near-identical accuracy
A Paradigm Shift to Assembly-like Finite Element Model Updating
-
Quantum method tracks nonlinear paths at 98% accuracy
A quantum nonlinear solver based on the asymptotic numerical method
-
Chirality flip lets flow model design better D-peptides
D-Flow: Multi-modality Flow Matching for D-peptide Design
-
Probabilistic ROM delivers fast cardiac predictions with uncertainty bands
A probabilistic reduced-order modeling framework for patient-specific cardio-mechanical analysis
-
Bi-level RL lifts trading Sharpe from 1.06 to 1.24
Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution
-
EEG cross-subject drops traced to variability or shortcuts by task type
What Causes Performance Degradation in Cross-Subject EEG Classification?
-
ActNet outperforms KANs in PINN benchmarks for PDEs
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
-
-
Graph penalty yields simpler network dynamics models
SINDyG: Sparse Identification of Nonlinear Dynamical Systems from Graph-Structured Data, with Applications to Stuart-Landau Oscillator Networks
-
Spline optimization lowers balun scattering parameter across frequencies
Isogeometric Shape Optimization of Multi-Tapered Coaxial Baluns Simulated by an Integral Equation Method
-
Random features replace gradient descent for fast accurate PINN training
Fast training of accurate physics-informed neural networks without gradient descent
-
FTX collapse shifts capital from centralized to decentralized exchanges
Trust Dynamics in Cryptocurrency Markets: Centralized vs. Decentralized Exchanges
-
Dual prompts raise credit scoring KS by 6.3 points in deployment
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting
-
Docking cast as graph match solvable on quantum annealers
Molecular Docking via Weighted Subgraph Isomorphism on Quantum Annealers
-
Single network matches ensembles in function-space Bayesian optimization
Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks