archive
Every paper Pith has read. Search by title, abstract, or pith.
85880 papers indexed · page 127
-
AI loop finds additives that raise perovskite cell efficiency
LEAP: A closed-loop framework for perovskite precursor additive discovery
-
UAV dataset lifts tracking success by 53 to 69 points
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
-
UAV dataset raises moving-target tracking success to 95 percent
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
-
LLM-rephrased notes keep broad utility but lose ICD details
Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale
-
Fine-tuned small models plan with tools without any catalog in the prompt
Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning
-
Tree constraints in training produce consistent plant skeletons
PlantPose: Universal Plant Skeleton Estimation via Tree-constrained Graph Generation
-
Framework makes one physical attack fool multiple AI vision tasks
Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework
-
Tensor decompositions match classical methods on 8-class MRI diagnosis
Multi-Class Neurological Disorder Prediction with Tensor Network Feature Engineering
-
Entropy-gradient inversion marks stronger reasoning in LRMs
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
-
Entropy-gradient inversion marks stronger reasoning in large models
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
-
Scheduler exposes tradeoffs across modular quantum hardware platforms
InterQ: Communication-Aware Scheduling Across Modular QPUs with Classical and Quantum Links
-
Age-only pension divisor subsidizes richer retirees in China
Mortality Heterogeneity and Actuarial Fairness in China's Notional Defined Contribution Pension System
-
Two GD steps produce multiple outliers in linear-width weights
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
-
Two GD steps yield floor(α2/(0.5-α1)) learned directions
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
-
Aligning latent mappings reduces inconsistency in multimodal models
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
-
Orthogonal subspaces disentangle context in healthcare models
AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models
-
Birth-death processes generate inflation-deflation count distributions
Stationary birth-death processes generating inflation-deflation distributions: Avoiding the issue of dominance
-
Test compares two categorical Gini correlations for predictor importance
Comparing Two Categorical Gini Correlations with Applications to Classification Problems
-
3-char neural tokens lift music fuzzy recall to 91.4%
Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search
-
Statistical views of user behavior improve insider-threat detection
MV-Gate: Insider Threat Detection via Multi-View Behavioral Statistics and Semantic Modeling
-
Unique Games admit tolerant testers with sublinear queries
Tolerant Testing for Unique Games
-
Pixel diffusion reaches FID 1.60 at 256 resolution in 320 epochs
FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
-
Language model agent orchestrates synthetic health data creation
Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets
-
Covariance rotations keep 2-bit KV caches accurate
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
-
Criteria for linear independence of polylog values proven
Linear independence of periods related to polylogarithms
-
Mixing ICD-9 and ICD-10 data lifts rare code F1 by 27 percent
Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes
-
Data favor sign-changing coupling in supergravity quintessence
Coupled quintessence with a potential from supergravity exhibits sign-changing interaction
-
Short trajectories train neural committor for fast kinetics
Fast and accurate committor estimation for kinetics simulations
-
Transient Rabi dynamics power all-optical neural networks
Optical Neural Networks from Coherent Transient Dynamics in Waveguide QED
-
Reversing tubing evolution recovers cosmological differential equations
An Alternative Viewpoint on Kinematic Flow from Tubing Splitting
-
NV spins drive motion in 128 mg levitated resonator
Spin-force from a Nitrogen-Vacancy ensemble drives a 100 mg levitated resonator
-
New measure exactly bounds full swap regret and tests from small samples
Testable and Actionable Calibration for Full Swap Regret
-
Adapter boosts Vision Transformer image quality assessment with fewer parameters
Unleashing Vision Transformer Potential In Image Quality Assessment via Global-Local Adaptive Interaction
-
Transposed Poisson structures on rank-(1+1) superalgebras are determined
On transposed Poisson conformal superalgebras
-
Actor-flow graphs structure AI experiment designs for governance
Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
-
Statistical analysis designs better quantizers for deep nets
StatQAT: Statistical Quantizer Optimization for Deep Networks
-
50% equity cap keeps pension decumulation nearly optimal
Numerical methods for optimal decumulation of a defined contribution pension plan
-
Sparsity experts and distillation enable continual adaptation
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
-
Uncertainty flow plus point cloud interaction cuts hand pose error
UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
-
Satisficing meets revenue targets by cutting worst-case shortfalls
From Optimization to Satisficing: Robust Screening under Distributional Ambiguity
-
Two-scale neural networks solve convection-dominated optimal control
Two-scale neural networks for optimal control of linear convection-dominated equations
-
Spectral multipliers give stable sphere approximation without exact cubature
Hyperinterpolation beyond exact cubature: a spectral multiplier approach
-
Wafer-scale III-V on SiN platform achieves under 25 mdB coupling loss
A Wafer-Scale Heterogeneous III-V-on-Silicon Nitride Quantum Photonic Platform
-
Phoneme profiles from real speech spot deepfakes of specific voices
Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection
-
Every projective variety realized as rank variety over generic hypersurface
Rank varieties over the generic hypersurface I
-
635-second X-ray period classifies source as intermediate polar
Classification of IGR J20084+3221 as an Intermediate Polar using X-ray and Optical Observations
-
Skill programs raise LLM agent results by 25% on web tasks
Harnessing LLM Agents with Skill Programs
-
Divergence fix straightens Rectified Flow trajectories
Divergence-Suppressing Couplings for Rectified Flow
-
Time-dependent Hurst exponent fits qubit 1/f noise better than constants
Non-Stationary Decoherence in Superconducting Qubits: Memory Multi-Fractional Brownian Motion and a Time-Dependent Quantum Brownian Motion Extension
-
New CG methods tridiagonalize non-Hermitian quaternion matrices
Structure preserving quaternion conjugate gradient-type methods for solving non-Hermitian quaternion linear systems