archive
Every paper Pith has read. Search by title, abstract, or pith.
506 papers in cs.CE · page 2
-
Discovery converts post-quantum uncertainty into prioritized accountability
Post-Quantum Discovery as a Governance Capability: Evidence-Based Cryptographic Visibility and Exposure Prioritisation in a Critical Service Provider
-
Benchmark scores LLM agents on 76 biomedical ML tasks
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
-
Decoupled subnetworks curb error growth in long PDE forecasts
Spatiotemporal decoupled physics-informed Stone-Weierstrass neural operator for long-time prediction of time-dependent parametric PDEs
-
Diffusion model refines protein structures from X-ray data 33x faster
CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography
-
Framework standardizes ML evaluations for nuclear fission and fusion
CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models
-
Reinforcement updates replace feedback loops in LLM alpha discovery
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
-
Bipartite GNN links nodes and elements for balanced forming predictions
Cross-attention-based bipartite graph neural network for coupled nodal and elemental field prediction in large-deformation sheet material forming
-
Two-stage model fuses radar and satellite for sharper rain forecasts
VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting
-
Transport-aware GNN and PPO optimize sparse flow reconstruction
Flow Field Reconstruction with Sensor Placement Policy Learning
-
ML model picks signal preemption times to limit side delays
Emergency Vehicle Preemption Strategies using Machine Learning to Optimize Traffic Operations
-
Chrono::Ray pairs simulation engine with distributed platform
Chrono::Ray: A Distributed Framework for High-Throughput Simulation-Based Analysis of Multibody Systems
-
Chrono::Ray links simulator to Ray for distributed multibody runs
Chrono::Ray: A Distributed Framework for High-Throughput Simulation-Based Analysis of Multibody Systems
-
Elastica++ is a new open-source software framework for fast
Elastica++: A high-performance, multiphysics framework for large interacting assemblies of Cosserat rods
-
AI surrogate runs 96-hour flood forecasts in 29 seconds
Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
-
Heating patterns control convection and entropy in power-law fluids
Effects of Thermal Boundary Conditions on Natural Convection and Entropy Generation in Non-Newtonian Power-Law Fluids
-
Vector quantization lifts stock return ranking accuracy
Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction
-
AD boosts JFNK solvers by 100-1000x with 95% completion
Robust Matrix-Free Newton-Krylov Solvers via Automatic Differentiation
-
Outcome-fair models still reason differently for similar applicants
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
-
Adaptive optimization reaches 0.73 AUC on shifted wildfire data
Environment-Adaptive Preference Optimization for Wildfire Prediction
-
Model recovery raises APDL automation completion to 92.7 percent
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation
-
Mapped wildfire surrogates match high-fidelity PDFs at 1000x lower cost
A geometry-aligned multi-fidelity framework for uncertainty quantification of wildfire spread
-
Scalable dispatcher handles millions of ride requests hourly
Advancing Dynamic Ride-Pooling Simulation -- A Highly Scalable Dispatcher
-
Hybrid neural models predict crash deformations at 3.20 mm error
Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention
-
Nonlinear embedding halves latent variables needed for glider shape accuracy
A nonlinear extension of parametric model embedding for dimensionality reduction in parametric shape design
-
LLM inference should be measured in joules per token at scale
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
-
Symmetry detection shrinks PDE library for exact recovery at 20% noise
EqOD: Symmetry-Informed Stability Selection for PDE Identification
-
The paper releases gym-invmgmt
gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods
-
Teacher-student PIDL ensemble improves traffic estimates for VSL scenarios
Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario
-
Sparse features steer LLMs to edit molecules toward target properties
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
-
Contract menus raise AI-RAN operator utility by 57 percent
Matching-with-Contracts for the AI-RAN Market: AIGC-as-a-Service for Teleoperation
-
Three parallelization strategies for PIF plasma schemes compared on supercomputers
On Distributed Parallelization Strategies for Particle-in-Fourier Schemes
-
Distributed NUFFT scales to 1024 GPUs on mixed hardware
A Performance-Portable, Massively Parallel Distributed Nonuniform FFT
-
Raspberry Pi system deploys Modbus sensor networks with one config file
A Flexible Raspberry Pi-Based Data Logger Platform for Modbus Sensors with Ansible Deployment
-
Online SAR processor focuses images line by line in 16 ms
Learning to Focus Synthetic Aperture Radar On-line with State-Space Models
-
Dual-head model gives calibrated forecasts without extra calibration
QuantWeather: Quantile-Aware Probabilistic Forecasting for Subseasonal Precipitation
-
One invariance rule unifies all AI explanation fairness metrics
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
-
The paper describes a computational framework that reconstructs moving heart geometries…
Image-Based Whole-Heart Cardiac Flow Simulations in Health and Congenital Heart Disease
-
LLM smart contracts score 8.29 points above human versions
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
-
History-aware operator halves rollout error for memory PDEs
HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations
-
History-space neural operator halves rollout error for memory PDEs
HS-FNO: History-Space Fourier Neural Operator for Non-Markovian Partial Differential Equations
-
78% of Matsumoto children reach high school in 90 minutes by transit
Evaluating Transit Accessibility to Education and Effects of Operational Delays in Japanese Regional Cities: A Case Study of Matsumoto City
-
Neural correction makes low-budget Monte Carlo PDE solves match 1000x compute
MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving
-
SuperMeshNet cuts HR data needs by 90 percent for mesh super-resolution
Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations
-
Agentic AI automates SPH workflows for debris flow modeling
Agentic AI for Particle-Based Simulation: Automating SPH Workflows for Debris Flow Modeling
-
AutoRedTrader achieves 69% misinformation exposure on trading agents
AutoRedTrader: Autonomous Red Teaming of Trading Agents through Synthetic Misinformation Injection
-
New Rao-Blackwellization cuts variance in MCMC light transport
Rao-Blackwellized Markov chain Monte Carlo Light Transport
-
Complex GAN metric separates gate-failure effects in circuits
Fault tolerance estimation in digital circuits with visualised generative networks
-
No significant performance gaps among four common GNN encoders
GraphNetz: Statistical Benchmarking of Graph Neural Networks with Paired Tests and Rank Aggregation
-
Schwarz framework refines MPM locally with up to 9x speedup
An Overlapping Schwarz Space-Time Refinement Framework for Material Point Method
-
Visibility nowcasts drop on new data due to distribution shifts
Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift