127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

research

29,816 results

Research

How Much Orthogonalization Does Muon Need?

DGX agent

arXiv:2606.00371v1 Announce Type: new Abstract: Muon optimizers improve neural-network training by replacing ill-conditioned momentum updates with approximately semi-orthogonal updates. This motivates

researcharxiv-cs-lg

2 Jun 2026

Research

How Neural Losses Shape VAE Latents

DGX agent

arXiv:2606.00635v1 Announce Type: new Abstract: Modern VAEs are rarely trained with the pointwise likelihood implied by the standard eta-VAE objective. In practice, pointwise reconstruction is often c

research

How Much Orthogonalization Does Muon Need?

How Neural Losses Shape VAE Latents

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image

Hybrid Probabilistic Forecasting of Under-Five Malaria Admissions in Ghana: A Gaussian Process Regression with Holt-Winters Smoothing

Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models

HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression

IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs

Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families

IDLM: Inverse-distilled Diffusion Language Models

iLRM: An Iterative Large 3D Reconstruction Model

IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset

Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images

Improved Belief-Attention in Vision Task

Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation

Improving IoT Intrusion Detection Through SMOTE-Based Oversampling and Extended Multi-Model Evaluation on Side-Channel Power Data

Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting

Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference

IMWM: Intuition Models Complement World Models for Latent Planning

In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise

Information-Theoretic Lower Bounds for Bit-Constrained Stochastic Optimization via a Reduction to Compressed Gaussian Mean Estimation

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms

Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation

Interpretable Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification using Multi-Omics Data

Interpreto: An Explainability Library for Transformers

Interventional Processes for Causal Uncertainty Quantification

Introduction to Graph Neural Networks for Machine Learning Engineers

Is Zero-Shot Super-Resolution Possible in Operator Learning?

It does what it says on the tin: safe synthetic data from coarsened margins

Iterated Population Based Training with Task-Agnostic Restarts

KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning

LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks

Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects

Learning from Saturated Data: Signals Beyond Correctness for LLM Training

Learning Hamiltonian Dynamics at Scale: A Differential-Geometric Approach

Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model

Learning Neural Deformation Representation for 4D Dynamic Shape Generation

Learning to Reduce Search Space for Generalizable Neural Routing Solver

Learning to Trim: End-to-End Causal Graph Pruning with Dynamic Anatomical Feature Banks for Medical VQA

Length Generalization Bounds for Transformers

Lessons from the Trenches on Reproducible Evaluation of Language Models

Limits of Resolution Equivariance in Fourier Neural Operators

Limits of Spatial Imagery Reasoning in Frontier LLM Models

Linear Motility Maps in Nonlinear Viscous Fluids