archive
Every paper Pith has read. Search by title, abstract, or pith.
85880 papers indexed · page 125
-
RL steers diffusion model to create better time-series forecasts from tiny data
DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data
-
Smartphone LiDAR sees hidden objects with motion sampling
Imaging Hidden Objects with Consumer LiDAR via Motion Induced Sampling
-
Wavelets represent time-varying thresholds in regime models
Wavelet Based Time Series Models with Time-Varying Thresholds
-
Second-stage correction cuts watch-time error by 12.57 percent
DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems
-
Freshness control lets async distillation match sync results
$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
-
Finite rank H(B) spaces equal domains of Toeplitz adjoints
Unbounded Toeplitz operators and finite rank de Branges-Rovnyak spaces
-
New multi-accent dataset lowers ASR errors on technical talks
PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions
-
Earring PPG achieves 2.3 bpm HR error
Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-site Wearables
-
Transformer picks antenna patterns for near-greedy HAPS beamforming
Transformer-Based Hybrid Beamforming with Reconfigurable Pixel Antenna for HAPS Communications
-
Socratic AI Tutor Outperforms Direct Answers for Young Coders
Towards SocratiCode: Designing a Generative AI-Based Programming Tutor for K-12 Students through a 4-Week Participatory Design Study
-
This paper introduces Knowledge Infrastructure (KI)
KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science
-
State-action decomposition adapts GRPO for VLM agents
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
-
State-action split lets GRPO train open-world VLM agents
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
-
Tensor Cores Speed 3D Gaussian Splatting Rendering by 1.65x
Accelerating 3D Gaussian Splatting using Tensor Cores
-
Tensor cores speed up 3D Gaussian splatting by 1.65×
Accelerating 3D Gaussian Splatting using Tensor Cores
-
Negative edges boost graph learning when labels are scarce
Learning over Positive and Negative Edges with Contrastive Message Passing
-
Graph cuts on tetra cells make remeshed models watertight by design
CelloCut: Constructive Watertight Remeshing via Tetrahedral Cell Cuts
-
UAV spacing trades computing access against task completion
CA3D: Computing Accessibility-Aware Cooperative 3D Deployment of Multiple UAVs
-
DexCoHand gripper cuts Astrobee base disturbances
A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation
-
Girsanov weights enable unbiased resampling for diffusion models
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
-
SynPro yields 3.7-5.2x more effective tokens from organic data
Generating Pretraining Tokens from Organic Data for Data-Bound Scaling
-
Weak coupling yields equilibrium in decentralized agent learning
Learning Empirical Evidence Equilibria under Weak Environmental Coupling
-
Weak coupling lets decentralized agents reach equilibria
Learning Empirical Evidence Equilibria under Weak Environmental Coupling
-
Zero-divisor graph invariants computed for F_p ring quotient
On Zero-Divisor Graph of the Ring $\frac{\mathbb{F}_p[u, v]}{\langle u^2,\, v^2, \, uv-vu\rangle}$
-
156-hour Urdu corpus supplies 12 paralinguistic labels
UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations
-
New metric tracks referee impact via win-probability shifts
Quantifying Officiating Impact in the NBA: A Referee Impact Metric Analysis Using ESPN Win-Probability Data
-
Recursive S_n structure proves specific molecule is a cell
Recursive structures of molecules and cells in Gelfand $S_n$-graphs
-
Symmetries classified for Ernst potentials in EMSF and ModMax
Potential Space Symmetries in Ernst-like Formulations of Einstein-Maxwell/ModMax-Scalar field Theories
-
Newton corrections enable parallel Transformer inference at 2.3x speed
SNLP: Layer-Parallel Inference via Structured Newton Corrections
-
Pedal input trends raise caregiver interest in stroke rehab game
A Collaborative Rehabilitation-Exercise Serious Game for People with Stroke and their Caregivers: A Pilot Study
-
Kerr black hole modes split and vanish near special frequencies via crossings and skipping
Pole Skipping, Avoided Crossing, and Resonant Excitation in Kerr Quasinormal Modes near Algebraically Special Frequencies
-
Pole tracking explains Kerr mode bifurcation and disappearance
Pole Skipping, Avoided Crossing, and Resonant Excitation in Kerr Quasinormal Modes near Algebraically Special Frequencies
-
Duality defect rises before crisis correlations
Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection
-
Retrieval system compresses Lean proofs over 70 percent
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
-
Bilevel optimization adapts distillation loss weights per sample
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
-
Fano factor of reset current transitions at affinity ln α
Network analysis for steady-state current fluctuations under finite affinity: Application to Brownian computation
-
Temporal pruning speeds video diffusion while preserving fidelity
Temporal Aware Pruning for Efficient Diffusion-based Video Generation
-
Temporal smoothing lets pruning speed up video diffusion
Temporal Aware Pruning for Efficient Diffusion-based Video Generation
-
Generic universal supersingular representations are non-admissible for n>=3
Non-admissibility of some universal supersingular representations
-
Femtosecond pulses track maxon pairs in superfluid helium
Coherent spectroscopy of collective excitations in superfluid helium far from equilibrium
-
Warm-up trick lets MeanFlow scale to 80B image models
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
-
One-step updates and barriers speed up noisy label correction
Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
-
Unquenched model links D_s1(2933) to mixed 2P state
Higher excited charmed and charmed-strange mesons in an unquenched quark model
-
Websites change fast so archiving must become routine
The Ephemeral Web and the Case for Proactive Archiving
-
Agentic planner cuts big data query latency by 23%
Agentic Cost-Aware Query Planning with Knowledge Distillation for Big Data Analytics
-
Memory-equipped agents show rising safety risks over time
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
-
Interactive AI needs new rules for judging trajectories
Interactive Evaluation Requires a Design Science
-
Energy minimization simplifies multigrid explanation
Multigrid Primer: Basic Principles
-
Orthogonal manifold moves identify content and style without independence
Content-Style Identification via Differential Independence
-
VLMs count by prior instead of image when facts clash
CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models