127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,664 results

Research

Kernel Treatment Effects with Adaptively Collected Data

DGX agent

arXiv:2510.10245v2 Announce Type: replace-cross Abstract: Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d. assum

researcharxiv-cs-lg

5 May 2026

Research

Kinematic Kitbashing

DGX agent

arXiv:2510.13048v2 Announce Type: replace Abstract: We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an

All entries

Kernel Treatment Effects with Adaptively Collected Data

Kinematic Kitbashing

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition

Knowledge-Based Design Requirements for Generative Social Robots in Higher Education

Kuo: OpenAI appears to be fast-tracking its AI agent phone with two NPUs and a custom MediaTek Dimensity 9600 SoC, targeting mass production as early as H1 2027 (@mingchikuo)

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

Lambda assembles leadership team to power gigawatt-scale AI infrastructure for the superintelligence era

Language models recognize dropout and Gaussian noise applied to their activations

Laplacian Frequency Interaction Network for Rural Thematic Road Extraction

Large Language Models for Multi-Robot Systems: A Survey

Large margin classifier with graph-based adaptive regularization

Last Week in AI #340 - OpenAI vs Musk + Microsoft, DeepSeek v4, Vision Banana

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference

Latent Space Probing for Adult Content Detection in Video Generative Models

Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation

LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images

Lateral String Stability for Vehicle Platoons: Formulation, Definition, and Analysis

Launch Week Livestream https://x.com/i/broadcasts/1RJZzjgBajbJB

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference

Learn more on our blog https://blog.comfy.org/p/luma-uni-1-is-now-available-via-partner

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Learning a Stochastic Differential Equation Model of Tropical Cyclone Intensification from Reanalysis and Observational Data

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation

Learning Discriminators for Resampling in the Ensemble Gaussian Mixture Filter through a Normalizing Flow Approach

Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions

Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning

Learning Koopman operators for coupled systems via information on governing equations of subsystems

Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning

Learning to Place Objects with Programs and Iterative Self Training

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot

Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure

Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy

Letter: UK-based Google DeepMind workers voted to unionize with the Communication Workers Union and Unite in April, representing 1K+ staff, amid the US DOD deal (Alice Speri/The Guardian)

Leveraging Argument Structure to Predict Content Hatefulness

Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise

Leveraging Ensemble-Based Semi-Supervised Learning for Illicit Account Detection in Ethereum DeFi Transactions

Leveraging Imperfect Medical Data: A Manifold-Consistent Spatio-Temporal Network for Sensor-based Human Activity Recognition

LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction

LiDAR for Rehabilitation: A Comprehensive Survey of Applications, AI Techniques, and Future Directions

LiDAR Teach, Radar Repeat: Robust Cross-Modal Navigation in Degenerate and Varying Environments

LIE: LiDAR-only HD Map Construction with Intensity Enhancement via Online Knowledge Distillation

Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation

Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion

Linear-Readout Floors and Threshold Recovery in Computation in Superposition

Linear-Time Global Visual Modeling without Explicit Attention

Linearizing Vision Transformer with Test-Time Training

LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery