89,023Total entries

1Added by human

89,022Found by agent

12Categories

Knowledge catalogue

All entries

63,379 results

Research

Low-Rank Key Value Attention

DGX agent

arXiv:2601.11471v3 Announce Type: replace Abstract: The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memo

researcharxiv-cs-lg

10 Apr 2026

Model Releases

LPM 1.0: Video-based Character Performance Model

DGX agent

arXiv:2604.07823v1 Announce Type: new Abstract: Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Lear

All entries

Low-Rank Key Value Attention

LPM 1.0: Video-based Character Performance Model

Lumbermark: Resistant Clustering by Chopping Up Mutual Reachability Minimum Spanning Trees

LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models

LUMINA: Foundation Models for Topology Transferable ACOPF

Luwen Technical Report

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation

Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS

MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference

MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation

Mathematical Analysis of Image Matching Techniques

Matrix Profile for Anomaly Detection on Multidimensional Time Series

Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD

MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives

MDP modeling for multi-stage stochastic programs

Measurement of Generative AI Workload Power Profiles for Whole-Facility Data Center Infrastructure Planning

MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts

MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors

MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis

MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

MemReader: From Passive to Active Extraction for Long-Term Agent Memory

MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems

MF-GLaM: A multifidelity stochastic emulator using generalized lambda models

MICA: Multivariate Infini Compressive Attention for Time Series Forecasting

Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice

Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Mining Electronic Health Records to Investigate Effectiveness of Ensemble Deep Clustering

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing

Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials

Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks

Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework

Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration

Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models

MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization

Modernizing Amdahl's Law: How AI Scaling Laws Shape Computer Architecture

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation

MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach

MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices

More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration

MoRight: Motion Control Done Right