archive
Every paper Pith has read. Search by title, abstract, or pith.
51070 papers indexed · page 9
-
Hyperbolic inverse curve flow solitons are axis graphs
The inverse curve shortening flow on the hyperbolic plane
-
Ruled surfaces critical for Dirichlet energy classified
Classification of the ruled surfaces that are critical points of the Dirichlet energy
-
Delta Forcing curbs drift in interactive video generation
Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation
-
Synthetic queries trigger up to 5x higher LLM failure rates
NodeSynth: Socially Aligned Synthetic Data for AI Evaluation
-
Synthetic augmentation lifts defense classification to 58% accuracy
Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
-
Data-augmented starts cut exploitability in hard-to-explore games
Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
-
Exploration fails above ceil(k/(n-2))-1 deactivations per round
Semi-Synchronous Exploration in Dynamic Graphs
-
Optimization finds optimal symbolic rules for classification
Optimal Pattern Detection Tree for Symbolic Rule-Based Classification
-
Coherent reuse turns stale gradients into O(1)-cost descent directions
Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
-
Damped beam reaches rest from boundary for all ρ ≤ 2 and almost all larger ρ
Boundary null-controllability for the beam equation with classical structural damping
-
Neural tangent kernel modulates kernels to control waveform inversion convergence
Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel
-
This paper proves that four subsets of primes whose lower densities sum pairwise above 1…
A density version of quaternary Goldbach problem
-
Geometry scores pick shallow layers for diffusion insertion in transformers
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
-
Model-based curricula speed motor skill learning by 23%
Automated Curriculum Design for High-dimensional Human Motor Learning
-
Semantic RL adds low-resource languages without erasing prior skills
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
-
Rank-r adapters enlarge implicit ensembles for tabular data
LoMETab: Beyond Rank-1 Ensembles for Tabular Deep Learning
-
Identifiable modules let models adapt to new sequences without erasing old knowledge
MoRe: Modular Representations for Principled Continual Representation Learning on Squantial Data
-
Entropy regularization yields equilibria for time-inconsistent games
Equilibrium for Time-inconsistent Mean Field Games: A Systematic Analysis by Entropy Regularization
-
Size filter trims 80 percent of tokens from LLM repo inputs
Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints
-
Projected mass, not spin splitting, sets altermagnetic Chern matter
From spin splitting to projected mass in altermagnetic Chern matter
-
Short concern texts track with activity drops and sleep issues
A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring
-
Mixture of experts speeds dynamic vector quantization 6-14x
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
-
Local strong solutions for fluid-elastic shell system
Well-posedness theorems in fluid-structure interaction: perfectly elastic shells
-
LLM filter and clustering finds 41 manipulative narrative clusters
LLM-based Detection of Manipulative Political Narratives
-
Transformers score German texts on left-right scale
Ideology Prediction of German Political Texts
-
Random stable atoms recover dynamic systems under physical priors
Randomized Atomic Feature Models for Physics-Informed Identification of Dynamic Systems
-
Adaptive sampling boosts worst-task performance in multi-task RL
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
-
Amorphous carbon monolayer shows Anderson criticality from disorder alone
Quantum Criticality in Monolayer Amorphous Carbon
-
Midpoint reference decouples pulsar frequency and derivative
A $Z_1^2$ framework for rotational-parameter estimation and uncertainty quantification in high-energy pulsars
-
Exemplar partitioning matches top SAEs at 1000x lower cost
Exemplar Partitioning for Mechanistic Interpretability
-
Frozen VFM stabilizes point-supervised infrared target detection
Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation
-
The paper shows that discrete sequences from difference inclusions converge if the…
Convergence of difference inclusions via a diameter criterion
-
NN radii converge almost surely under polynomial mixing
Nearest-Neighbor Radii under Dependent Sampling
-
Physics-guided diffusion generates spectrally accurate satellite imagery
AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors
-
The paper introduces a framework that refines pseudo-audio prompts by explicitly modeling…
Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR
-
Predictive AI adapts SBFD uplink-downlink splits
Sub-Band Full Duplex Resource Allocation: A Predictive Deep Reinforcement Learning Approach
-
Illumination-guided diffusion restores complex night scenes
IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
-
Boussinesq equation well-posed on half-line with Robin conditions
The "good" Boussinesq equation on the half-line with Robin boundary conditions
-
Secrecy for multimodal wiretap coding splits into three parts
Secure Joint Source-Channel Coding of Multimodal Semantic Sources
-
Localized losses boost text and face fidelity in image tokenizers
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
-
Single trained operator solves multi-agent control in sub-seconds
PI-SONet: A Physics-Informed Symplectic Operator Network for Real-Time Optimal Control of Multi-Agent Systems
-
Analog RF computing slashes client energy for edge AI by ~100x
Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems
-
Moderate starters gain most in AI agent workshops
Computational Thinking Development in AI Agent Creation_A Mixed-Methods Study
-
Unified definition unifies conventional and quantum ferroelectrics
Unified definition of ferroelectricity
-
Token module improves DDI predictions for unseen drugs
AIM-DDI: A Model-Agnostic Multimodal Integration Module for Drug-Drug Interaction Prediction
-
Dual priors from DEM and clouds control remote sensing image generation
D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog
-
Optimal rate O(k^{2/(1-q)}) holds for any ℓ_p norm
Convergence Rates for $\ell_p$ Norm Minimization in Convex Vector Optimization
-
Dynamic Latent Routing beats supervised fine-tuning by 6.6 points
Dynamic Latent Routing
-
One-time pass leaves subtraction Nim Grundy rule unchanged
A Subtraction Nim with a Pass
-
Adaptive metrics boost convergence in vector optimization approximation
Adaptive Metrics for Norm-Minimization-Based Outer Approximation in Convex Vector Optimization