127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

34,859 results

Research

On the Convergence of Muon and Beyond

DGX agent

arXiv:2509.15816v5 Announce Type: replace Abstract: The Muon optimizer has demonstrated remarkable empirical success in handling matrix-structured parameters for training neural networks. However, a s

researcharxiv-cs-lg

12 May 2026

Research

On the Convergence Rate of LoRA Gradient Descent

DGX agent

arXiv:2512.18248v3 Announce Type: replace Abstract: The low-rank adaptation (LoRA) algorithm for fine-tuning large models has grown popular in recent years due to its remarkable performance and low co

Search: “research”

On the Convergence of Muon and Beyond

On the Convergence Rate of LoRA Gradient Descent

On the global convergence of gradient descent for wide shallow models with bounded nonlinearities

One-step Latent-free Image Generation with Pixel Mean Flows

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory

Online Set Learning from Precision and Recall Feedback

Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection

Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions

Optimal Regret for Single Index Bandits

Optimizer-Induced Mode Connectivity: From AdamW to Muon

Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks

ORICF -- Open Robotics Inference and Control Framework

OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns

Outlier detection for patient monitoring and alerting

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner

OZ-TAL: Online Zero-Shot Temporal Action Localization

P-Flow: Proxy-gradient Flows for Linear Inverse Problems

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers

PACT: Peak-Aware Cross-Attention Graph Transformers for Efficient Storm-Surge Emulation

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding

PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering

Perceptual Asymmetry Between Hue Categories: Evidence from Human Color Categorization

Performance and Energy Trade-Off Analysis of Hierarchical Federated Learning for Plant Disease Classification

PGID: Progressive Guided Inversion and Denoising for Robust Watermark Detection

Phase Transitions in Affective Meaning Divergence: The Hidden Drift Before the Break

Phases of Muon: When Muon Eclipses SignSGD

Physics-Informed Neural PDE Solvers via Spatio-Temporal MeanFlow

PIDNet: Progressive Implicit Decouple Network for Multimodal Action Quality Assessment

Pixal3D: Pixel-Aligned 3D Generation from Images

PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams

Positive Alignment: Artificial Intelligence for Human Flourishing

Post-hoc Selective Classification for Reliable Synthetic Image Detection

PowerStep: Memory-Efficient Adaptive Optimization via ell_p-Norm Steepest Descent

Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World

Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns

Predicting Large Model Test Losses with a Noisy Quadratic System

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective

Predictive Radiomics for Evaluation of Cancer Immune SignaturE in Glioblastoma: the PRECISE-GBM study

Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data

Private Vertical Federated Inference for Time-Series

Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation

Probing Cross-modal Information Hubs in Audio-Visual LLMs

Probing Routing-Conditional Calibration in Attention-Residual Transformers

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability

Progressive Photorealistic Simplification

Projection-Free Functional Constrained Optimization for Risk Aversion and Sparsity Control

PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis