archive
Every paper Pith has read. Search by title, abstract, or pith.
85880 papers indexed · page 124
-
Reformulated complementarity enables single-precision IPM solvers
A Differentiable Interior-Point Method in Single Precision
-
Benchmark adds touch, RL training, and real robots to world model tests
WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
-
Benchmark turns NASA mission text into logic formulas
A Pilot Benchmark for NL-to-FOL Translation in Planetary Exploration
-
Debiased ML recovers continuous treatment effects in panel data
Double/Debiased Machine Learning for Continuous Treatment Effects in Panel Data with Endogeneity
-
Compiler enforces AI rules in constant time with formal proofs
Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI Systems
-
Operators display Mpemba effect under adjoint Liouvillian
Quantum Mpemba effect for operators in open systems
-
One model translates any sensor features to any other without retraining
One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception
-
Global resetting maps multi-particle exits to diffusion moments
Global resetting and emergent correlations: exit statistics in an interval
-
Curriculum learning boosts multi-UAV ISAC sensing by over 30 percent
Curriculum-Guided Heterogeneous Multi-Agent Intelligence for Multi-UAV Cooperative ISAC
-
Multi-UAV ISAC sensing rises over 30 percent with curriculum learning
Curriculum-Guided Heterogeneous Multi-Agent Intelligence for Multi-UAV Cooperative ISAC
-
Frequency disentanglement plus geodesic matching lifts few-shot medical segmentation
Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation
-
AI chunking builds maps predicting war in Thucydides model
Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap
-
Literature evidence anchors stochastic degradation model choice
LAST-RAG: Literature-Anchored Stochastic Trajectory Retrieval-Augmented Generation for Knowledge-Conditioned Degradation Model Selection
-
Bi-LSTM emulator adapts VCSEL PAM-4 models 20 times faster
VCSEL-based PAM-4 transmission system emulator: A data-driven deep learning perspective
-
Nilpotent orbits in duality image are quasi-admissible for all types
Quasi-admissible, raisable nilpotent orbits and covering Barbasch-Vogan duality
-
LLM voice agent hits 83.9% success on 400k daily calls
DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
-
Single forward pass matches AlphaFold3 protein accuracy
DCFold: Efficient Protein Structure Generation with Single Forward Pass
-
C++ library runs GP inference up to 8x faster than GPyTorch on M4
Lightweight Gaussian Process Inference in C++ on Metal and CUDA
-
Sulfur doping multiplies carbon nitride H2O2 output sixteenfold
Metal-free heteroatom doping of carbon nitride for enhanced photocatalytic hydrogen peroxide production
-
Innovation attracts more foreign equity than debt investment
The Effects of Innovation on Foreign Portfolio Investment: The Role of Institutions and Risk-Taking
-
Quantum prototypes in Hilbert space beat classical methods
Geometric Prototype Learning in Quantum Hilbert Space with Matrix Product States
-
Benchmark rates AI agents by child cognitive age
Evaluating Cognitive Age Alignment in Interactive AI Agents
-
Depth-guided flash simulation improves low-light photos
LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers
-
JSON IR and compiler checks lift LLM circuit correctness
CPPL: A Circuit Prompt Programming Language
-
DistilBERT reaches 99.78% accuracy on mixed phishing datasets
Explainable Machine Learning for Phishing Detection on Heterogeneous Datasets with MCP-Enabled Deployment
-
Superconductivity found in seven-layer graphene without moiré
Multiple Superconducting Phases in Rhombohedral Heptalayer Graphene
-
CoX-MoE raises MoE throughput up to 7.1x with CPU-GPU collaboration
CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution
-
Neural net forecasts wall turbulence 300 steps ahead
Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis
-
Inter-layer null signals cut attention sinks and boost quantized accuracy
Attention Sinks and Outliers in Attention Residuals
-
Game theory models control of human-tech systems
Cooperative and Noncooperative Paradigms for Game-Theoretic Control of Socio-Technical Systems
-
AI agent teams beat human teams at generating creative ideas
Multi-agent AI systems outperform human teams in creativity
-
Egglog turns higher-order math models into natural LaTeX and fast constraints
Optimizing Optimizations, Declaratively: Optimizing the Higher-Order Functions in Mathematical Optimization with egglog
-
Random block updates on both sides give O(1/K) rate for saddle-point problems
On the convergence of doubly stochastic Primal-Dual Hybrid Gradient Method
-
Source confusion slows depth gains for GREX-PLUS
Assessing the Impact of Source Confusion for GREX-PLUS based on Deep JWST NIRCam Imaging
-
Hotter isotropic granular gas relaxes faster than cooler sheared state
Mpemba effect in a sheared granular gas with velocity-dependent restitution
-
Tableaux count Schur coefficients for two-row Lie modules
Thrall's problem for two rows
4 Piths -
Two-phase sampling matches contradictory audio prompts to video
CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
-
Guard boosts training utilization 1.7x by catching hidden stragglers
Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training
-
Phase tunes bound-state count in giant-atom waveguides
Bound state in the continuum and dynamics via phase modulation in giant-atom waveguide setups
-
Internal probe plus attention head yields step rewards for agents
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
-
Flat connection loops characterize minimal Lagrangian surfaces
Minimal Lagrangian surfaces in the two-dimensional complex hyperbolic quadric via the loop group method
-
Mamba model beats SOTA on ECG multi-label scores
HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities
-
Crosscap transpositions realized as monodromies of M-singularities
Realizing crosscap transpositions as monodromies of singular fibrations
-
Hindsight targets fix actions to cut agent training time 2.26x
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
-
Exact q-adic valuation formula for σ_k(n) via LTE
A note on the $q$-adic valuation of $\sigma_k(n)$
-
GUI tool structures Monte Carlo workflows into reusable units
MAGE-HEP: Monte Carlo Analysis and Graphical Environment for High-Energy Physics
-
Rotating black holes gain primary hair in 5D Proca theory
Rotating black holes with primary hair in five-dimensional generalized Proca theory
-
Classical SIFT beats learned descriptors on accuracy and speed
PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines
-
Correlated datasets bias sequential Bayesian updates
Sequential Bayesian inference with correlated heavy-ion datasets
-
Hybrid storage splits roles to capture arbitrage and reserve profits
Profit-Oriented Planning and Multi-Market Operation Model for Hybrid Energy Storage Systems