127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,604 results

Model Releases

llm-gemini 0.32a0

DGX agent

I don't have current information about this specific entry, so I'll describe what it likely covers based on the available details. This entry documents the release or update of llm-gemini version 0.32

model-releasessimon-willison

19 May 2026

Agents

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

DGX agent

arXiv:2605.18077v1 Announce Type: new Abstract: Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on i

All entries

llm-gemini 0.32a0

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

LLM-Safety Evaluations Lack Robustness

LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

LLMs for automatic annotation of Mandarin narrative transcripts

LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations

llms.txt validation will be supported in Chrome devtools :)

Locally Coherent Parallel Decoding in Diffusion Language Models

LogRouter: Adaptive Two-Level LLM Routing for Log Question Answering in Big Data Systems

Long Context Modeling with Ranked Memory-Augmented Retrieval

Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior

LoopQ: Quantization for Recursive Transformers

Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation

Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning

Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

Low Latency Gaze Tracking via Latent Optical Sensing

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

LSDTs: LLM-Augmented Semantic Digital Twins for Adaptive Knowledge-Intensive Infrastructure Planning

LTX 2.3 i2v - color/brightness/contrast change

LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

M^2FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices

MA^{2}P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion

Machine Learnability as a Measure of Order in Aperiodic Sequences

Machine Learning-Based Pre-Test Risk Stratification for PCR-Confirmed Chlamydia Using Patient-Reported Data and Urine Biomarkers

Machine Learning Enabled Graph Analysis of Particulate Composites: Application to Solid-state Battery Cathodes

Machine Unlearning for Masked Diffusion Language Models

Machines Learn Number Fields, But How? The Case of Galois Groups

MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop

Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory

ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics

MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment

Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems

Markerless Motion Capture for Biomechanical Whole-Body Kinematic Estimation in Infants

MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization

MARS: Technical Report for the CASTLE Challenge at EgoVis 2026

MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation

Masking Causality and Conditional Dependence

MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings

Matern Gaussian Processes on Graphs

@mathurahravi This by @swyx is some of the best writing on the internet https://www.swyx.io/create-luck

Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards