127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “safety”

22,398 results

Model Releases

Qwen3.5-9B Triple-Loop

DGX agent

I was fascinated by Nanbeige's outstanding performance for its size, so I started digging into how much a model can improve its own representation just by looping over itself (for fun). My prototype w

model-releasesr-localllama

23 Aug 2026

Model Releases

Search: “safety”

Qwen3.5-9B Triple-Loop

A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model

CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios

Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts

ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models

EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

How agents can delegate better

Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms

Where Security Fits in an AI Agent Stack

10 questions every startup should answer before moving to production with their AI prototype

3 days benchmarking most llama.cpp flags on my weird 40gb vram laptop + tb4 egpu setup. Got +70% generation, +40% prefill, 60k more context, and filed a bug in llama around MTP. What I learned.

A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation

Breaking the weakest link to evade vision language models

EVADE: Evidence-Verified Agentic Diagnosis with Escape

MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations

Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents

An Investigation of the NeurIPS and ICML 2025 Position Tracks

Inference-Time Attention Steering for Vision-Language-Action Driving Models

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

OOD Detection for EEG-based Machine Learning in High-Risk Environments

The 10th AI City Challenge

Vision-Language Models for Analog Gauge Reading: An Empirical Study of Specialization, Transfer and Reliability

AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving

ARENA: Automated Red-Teaming for Large Audio Language Models

Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation

Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration

DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence

FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making

Governance on autopilot, minus the turbulence

I built a local AI workspace for Windows and finally released it

OGX: An Open-Source, Vendor-Neutral Generative AI Application Server

OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models

Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning

Physiological World Models for Human State Transitions

PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails

Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression

Toward Better Assessment of LLMs' Performance in Clinical Error Detection

Whose Gold? Annotator-Pool Disagreement Is Large at the Item Level, and Hidden by Small Leaderboards

After pushing 1M+ tokens through Qwen 3.8 27B, here is my optimal llama.cpp config for 16GB VRAM (73k Context, Agentic Coding)

Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents

AgentRewind: Recoverable Execution for Long-Horizon LLM Agents

Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions

High-dimensional nonparametric changepoint detection via low-rank degree-two density projection

Many people’s blindness to this problem — AI failing to follow instructions — is like their initially blasé attitude towards hallucinations,…

NAST: Improving Negation Handling in Medical Vision-Language Models through Negation-Aware Selective Training

Dear Dario, 1. If Claude can cure cancer to save people like your dad, why should we 'pace the progress'? Does that mean more people with He…

Qwen3.8-27b on RTX 3090 - 82 tps single request, up to 672 tps peak