archive
Every paper Pith has read. Search by title, abstract, or pith.
506 papers in cs.CE · page 3
-
ML interatomic potentials fail compositional tests on unseen molecules
Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
-
Anisotropic diffusion retains geometry to improve generative image quality
Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations
-
Model turns protein sequences into interaction descriptions
PPI2Text: Captioning Protein-Protein Interactions with Coordinate-Aligned Pair-Map Decoding
-
Diffusion Restore makes MCMC light transport real-time
Diffusion Restore: Real-Time Markov Chain Monte Carlo Light Transport
-
Diffusion Restore achieves real-time MCMC light transport
Diffusion Restore: Real-Time Markov Chain Monte Carlo Light Transport
-
Diffusion dynamics make MCMC light transport run in real time
Diffusion Restore: Real-Time Markov Chain Monte Carlo Light Transport
-
SGRPO widens the utility-diversity frontier in biomolecular design
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
-
SGRPO widens biomolecular utility-diversity frontier
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
-
Texture liking raises burger appeal by 0.28 points independently
Texture Independently Drives Liking in AI-Generated Alternative Protein Burgers
-
Stencil kernels run up to 342x faster on wafer-scale engine
Stencil Computations on Cerebras Wafer-Scale Engine
-
Quantum-inspired method tops solvers in non-convex ML tasks
Exploring the non-convexity in machine learning using quantum-inspired optimization
-
Fixed retraining every five batches outperforms tuning in semiconductor AI
Robust and Reliable AI for Predictive Quality in Semiconductor Materials Manufacturing with MLOps and Uncertainty Quantification
-
Plasma simulations need three post-Moore tech tiers
Post-Moore Technologies for Plasma Simulation: A Community Roadmap
-
Physics constraints improve low-data flow predictions in stirred tanks
Accelerated and data-efficient flow prediction in stirred tanks via physics-informed learning
-
Exact repairs improve physical forecasts only when aligned with data
Exactness Matters for Physical Rule Enforcement
-
QuadNorm removes resolution dependence in neural operators
QuadNorm: Resolution-Robust Normalization for Neural Operators
-
S-SPH reduces stochastic mechanics costs by up to 1000x
Stochastic Smoothed Particle Hydrodynamics for Stochastic Mechanics Problems
-
Hierarchical split scales aperiodic metamaterial design
Scalable Active Metamaterials for Shape-Morphing
-
Adaptive coordinates boost neural PDE operator accuracy
Adaptive Coordinate Transforms for Neural Operators
-
Arbitrage stabilizes AMM tracking error geometrically under block correction threshold
Arbitrage and the Stability of AMM Price Tracking
-
Sparse models required for quantum RIS optimization on NISQ hardware
Quantum Optimization for Electromagnetics: Physics-Informed QAOA for Reconfigurable Intelligent Surfaces
-
Duplicate-aware Carleman linearization cuts monomial overhead
Duplicate-Aware Shift-and-Lift Carleman Linearization:Structure, Complexity, and Comparative Evaluation
-
Sano model best matches shell results on ribbon buckling shifts
Discrete Elastic Ribbons: A Unified Discrete Differential Geometry Framework for One-Dimensional Energy Models
-
FFT solver fastest for electrostatic PIC plasma simulations
A Comparison of Massively Parallel Performance Portable Particle-in-Cell schemes for electrostatic kinetic plasma simulations
-
Camera vision narrows mmWave beam search for vehicles
Look Once, Beam Twice: Camera-Primed Real-Time Double-Directional mmWave Beam Management for Vehicular Connectivity
-
Grid overlay beats semantic prompts for LLM chart reading
Spatial Priming Outperforms Semantic Prompting: A Grid-Based Approach to Improving LLM Accuracy on Chart Data Extraction
-
DATO and QMDA take different routes in data assimilation
From Classical to Quantum-Mechanical Data Assimilation: A Comparison between DATO and QMDA
-
SIMP density field initializes level-set for sharp 3D boundaries
Sequential topology optimization: SIMP initialization for level-set boundary refinement
-
Blockchain verifies fair trade labels without central trust
A Blockchain-as-a-Service Solution for TAFES-Compliant Verification of Fair Trade Certifications
-
Rules plus models raise accuracy for Vietnamese NER with scarce labels
A Hybrid Method for Low-Resource Named Entity Recognition
-
Peridynamics model links waves and buoyancy to ice shelf calving
How Do Ice Shelves Calve? Peridynamic Modeling of Ice Shelf Fracture Driven by Wave Erosion, Basal Melting, and Buoyancy Flexure
-
Algorithm distributes points on curved surfaces with prescribed local spacing
Globally adaptive and locally regular point discretization of curved surfaces
-
Joint scheduling of AI jobs and microgrid power raises benefits and cuts emissions
Carbon-Aware Compute--Power Scheduling for AI Data Centers with Microgrid Prosumer Operations
-
Joint MILP lifts AI data center benefits and cuts emissions
Carbon-Aware Compute--Power Scheduling for AI Data Centers with Microgrid Prosumer Operations
-
Early thrombus shapes virtual DSA views after aneurysm device placement
Device-Induced Thrombus Formation in Cerebral Aneurysms: Linking Patient-Specific Clot Modeling and Functional Occlusion to Virtual Angiographic Assessment
-
Graph fusion model tightens stock price prediction intervals
Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval
-
Hybrid model predicts composite deformation above training temperatures
Hybrid Machine Learning and Physical Modeling of Feedstock Deformation During Robotic 3D Printing of Continuous Fiber Thermoplastic Composites
-
The paper defines two new classes of causal models for decision-making agents: Structural…
The Design and Composition of Structural Causal Decision Processes
-
Quantum models match classical baselines on financial time series
Learning Temporal Patterns in Financial Time Series: A Comparative Study of Quantum LSTM and Quantum Reservoir Computing
-
Stress cuts LLM agent quality by a third but flags learnable structure
When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
-
Stress cuts LLM quality by one third yet reveals antifragile structure
When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
-
Perturbative model fixes 22% heating load errors in variable walls
Perturbative Analytical Framework for Thermal Wave Diffusion in Non-linear Building Envelopes
-
The paper builds a dataset of 150 homicide cases annotated with 17 legal concepts and…
Can Causal Discovery Algorithms Help in Generating Legal Arguments?
-
Holomorphic potentials plus single energy loss train accurate 2D fracture networks
A Variational Kolosov--Muskhelishvili Network for Elasticity and Fracture
-
Diffusion model generates optimal structures in seconds with <1% error
Diffusion Transformers with Hybrid Conditioning for Structural Optimization
-
Representation constraints keep refusal behavior intact after LLM fine-tuning
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
-
Electrolyte wetting in cracks raises particle capacity 25% above uniform-flux forecasts
On the role of crack electrolyte wetting in the degradation and performance of battery active particles
-
The paper proposes the Visibility Graphs Relative Strength Index (VGRSI)
Visibility graphs can make money in financial markets
-
Neural geometry couples to multiphysics solver for joint transient optimization
Differentiable Multiphysics Co-Optimization via Implicit Neural Representations: A Transient Hamburger-Cooking Benchmark
-
Policy learns to compose PDE modules for order-of-magnitude OOD gains
HyCOP: Hybrid Composition Operators for Interpretable Learning of PDEs