archive
Every paper Pith has read. Search by title, abstract, or pith.
75412 papers indexed · page 44
-
Joint action-predicate model enables zero-shot robot skill composition
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
-
Twin-focus method lifts 1 PW laser Strehl ratio to 0.80
HotLoop Optimization of Petawatt Laser Focal Spot via a Twin-Focus Scheme
-
AI turns social media into unified index of disaster physical and social toll
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
-
Paired clean videos train model to recognize actions in fog
Seeing Through Fog: Towards Fog-Invariant Action Recognition
-
RL method produces ready-to-bend pipes for aeroengines
Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines
-
Self-distillation balances consensus across views to cut noise from privileged signals
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
-
Hard labels beat soft labels with sparse annotator votes
Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions
-
LLM compilation creates hidden backdoor attack surface
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
-
Training supervision lifts portrait alignment
Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
-
Weak-form latent models cut PDE optimization time by five orders
Time-Dependent PDE-Constrained Optimization via Weak-Form Latent Dynamics
-
C-ALADIN converges globally for convex consensus optimization
Distributed and Decentralized Optimization Algorithms via Consensus ALADIN
-
PUBO reformulation lets FALQON compute MSTs for OPF prototypes
PUBO Formulation for MST and Application to Optimum-Path Forest
-
Continuous timing lifts growth-defensive ETF allocation
Continuous Timing Signals for Growth-Defensive Style Allocation: Factor Attribution, Risk Matching, and Out-of-Sample Evidence
-
Localization method builds Transformers from local kernels
The General Theory of Localization Methods
-
Smoothing with auxiliary sample gives regression confidence regions
New Confidence Regions for Linear Regression Parameters with Stationary-Ergodic Dependent Errors
-
AIPW stays stable when propensity models are wrong
Application of Propensity Score Models and Causal Estimators in Observational Studies under Model Misspecification
-
Magnetar jet unifies thermal
Multi-wavelength Emission for a Post-merger Magnetar: The Magnetar-Driven Poynting Jet and Its Associated Pulsar Wind Nebula
-
Phonon modes imprint sidebands on high-harmonic spectra
Probing Lattice Dynamics in Real-Space and Real-Time
-
Temporal cache delivers 30.6x speedup on hits in agent pipelines
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
-
Splitting and merging unify graphs
An axiomatic framework from splitting and merging in MAT-labeled graphs, vines, and single-peaked domains
-
Divide-prompt-refine produces more novel biomedical abstracts without training
Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation
-
Elliptic curve pseudorandom vectors bound by sqrt(q)/t under period condition
On discrepancy estimates for pseudorandom vectors constructed by the elliptic curve congruential generator
-
Pipeline triples accuracy for Indigenous image captions
Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
-
TTR metrics unify priority and safety for aerial vehicle merging
Time-To-Reach Separation and Safety Filtering for Safe, Fair, and Efficient Multi-Agent Coordination
-
Autoregressive diffusion cuts video restoration latency to seconds
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
-
AI generates proofs for lower bounds on advection-diffusion mixing
Lower Bounds for Advection-Diffusion Equations: An Exploration with AI-Generated Proofs
-
Faint galaxies supply metals to the early CGM
Connecting CGM enrichment with Lyman alpha emitters at 2.9 < z < 6.7
-
New model detects category shifts in periodic time series
Changepoint Detection in Categorical Time Series with Application to Daily Total Cloud Cover in Canada
-
Local updates cut Shapley recompute cost by 1000 times
Dynamic Shapley Computation
-
CDF inversion fixes uneven Pareto front sampling
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
-
Agents learn when to jump in vehicle routing search
COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search Space
-
Any concave spectrum realized exactly by some continuous potential
Complete realization of multifractal entropy spectra
-
Offline consolidator cuts agent memory 12x while raising success
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
-
Imputation recovers causal effects from censored mediators
Evaluating causal indirect effects when mediators are left-censored by assay limit of quantification
-
Metal-poor star's r-process pattern matches merger models
The \emph{R}-process Alliance: A Bright, Strongly \emph{R}-process-enhanced Extremely Metal-poor Star Observed with GHOST
-
1B model scores 60.7% on MMLU after 40B instruction tokens
HRM-Text: Efficient Pretraining Beyond Scaling
-
Nested concept models reduce intervention costs to O(log K)
Matryoshka Concept Bottleneck Models
-
Bel-Robinson decomposition defines entropy in type I spacetimes
Gravitational entropy in Petrov Type I spacetimes
-
Animate-inanimate split structures vision MoE experts stably
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
-
Latent analogies compose optimal plans for unseen goals in offline RL
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
-
Multi-agent system cuts 5G repair time by 86 percent
From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)
-
Vision model separates content from style to assure landing safety
Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
-
-
Hybrid resonators merge plasmonic boost with dielectric efficiency
Engineering Hybrid Resonances in Nanophotonics
-
New depth ranks sparse functional data without reconstruction
Conditional regularized halfspace depth for sparse functional data and its applications
-
t-admissible subgraphs determine regularity of symbolic powers
Critical subgraphs and the regularity of symbolic powers of cover ideals of graphs
-
Self-training amplifies surface markers while deep syntax dies
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
-
Control function identifies quantiles despite endogeneity and error
Endogenous Quantile Regression with Measurement Error in Dependent Variable
-
High-volume eviction counsel scales filings without raising defaults
High-Volume Plaintiff-Side Counsel and Single-Appearance Eviction Cases in Philadelphia
-
Empirical Bayes reuses data twice and misses true posterior uncertainty
An Old Look at Empirical Bayes