127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “persistence”

4,971 results

Agents

Bioinfoysis Technical Report

DGX agent

arXiv:2609.03871v1 Announce Type: new Abstract: Large language model agents have shown promise in bioinformatics, but most existing systems focus primarily on producing final answers, treating plannin

agentsarxiv-cs-ai

4 Sept 2026

Model Releases

FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models

DGX agent

Search: “persistence”

Bioinfoysis Technical Report

FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models

Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chains

Transfiver: Human-AI Co-Inference through a Shared Editable State

Introducing Quartermaster, an open source local AI platform designed for ease of use that does not sacrifice customizability

We need a better taxonomy for what people are calling 'continual learning'

What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we des…

Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

Claude's new system prompt really doesn't want to reproduce song lyrics

Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure

H3-World: Turning Language Understanding into World Control

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations

Safin-1: Safety from Within through Memory-Native State Evolution

Training-Free Inpainting Across Domains with a Frozen Text-to-Image Diffusion Model

Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction

Benevolent Bias in Multi-Turn Human-Agent Dialogue

EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production

From the Loss Landscape to Diverse Feature Learning in Neural Networks

Integrating adaptive human behavior into epidemic models with large language models

JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees

Liquid Gated Attention

Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion

Predicting Future Organ Dysfunction in ICU Patients Using Temporal Convolutional Networks on MIMIC-IV Data

Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation

SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation

Update: llama.cpp for Radeon VII / MI50 / MI60 — +14% PP, +9% long-context fill vs upstream + adaptive Flash Attention

AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction

An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models

Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experience

INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents

The Cold-Start Safety Gap in LLM Agents

Canalization Before Generalization: Grokking as a Dynamical Probe

Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions

CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search

Running local LLM's as agents in Claude Code

Towards safe and optimal flight: Viability Kernel MPC for Fully Actuated Multirotor

Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios

A Behavior-Guided Online Probabilistic Forecasting Method for Electric vehicle Charging Loads

AURASeg: Attention-Guided Upsampling with Residual-Assisted Boundary Refinement for Drivable-Area Segmentation

Disentangled Skill Representations for Predictive Human Modeling

DreamLedger: Execution-Settled Credit Files for World-Model Imagination in Robot Decision Loops

LumiXAI: A Modular Full-Stack Framework for Feature Attribution

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

StateTune: Transforming LLM-Assisted EDA Flow Tuning into a Stateful, Closed-Loop Process

Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities

Where World Models Break: Natural-Input Failure Discovery