AI Wiki — Knowledge Base

I turned Qwen3.8-27B Q2_64 + llama.cpp into a fully TypeSafe AI-compatible Jev-like system. OpenAI API still intact! World’s first Vision-enabled Jev-like model! <10 GB VRAM, 170 ms on an RTX 3090 and ~140 tok/s in chat. 76% vs. 88% Jev-1.13 Acc. on a diverse 22,000-request typed-decision benchmark

Yesterday I released Bonsai-Llama-Jev - a Jev-like Typed Decision inference system for locally operated, sovereign AI. In my new typed-decision-bench, covering more than 22,000 decisions across 175 us

model-releasesr-localllama

23 Sept 2026

Search: “multimodal”

Copy-Move Forgery Detection and Question Answering for Remote Sensing Image

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Evaluation of pre-trained models for pedagogical assessment of novel AI-assisted educational questions

How growing Latin American midsize businesses are building in the AI era

Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents

Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents

Learning the Cost of Reliable Inference

Lend me an Ear: Speech Enhancement Using a Robotic Arm with a Microphone Array

Listening and Mirroring: The Effects of Verbal Attunement and Behavioral Mimicry on Social and Empathic Perceptions of Embodied AI Agents in VR

Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams

Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts

MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos

NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task

NV-Reason-CT: 3D Visual Language Model for CT Analysis

PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer

Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care Residents

Power your agents: Gemini 3.8 Live with Live Avatar is now generally available

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

RoboCafe in the Open: Interaction Continuity in Long-Term Public Human-Robot Interaction

The three things today's hottest startups are looking for in their AI stack

Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction

A Reconfigurable Bidirectional Cable-Driven Hip Exoskeleton with Swappable Bench/Backpack Dual-configuration Actuation

Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation: A Case Study in Decision Support for Rice Cultivation in Japan

BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease Diagnosis

Calibrated Confidence Expression for Radiology Report Generation

Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow

From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving

Introducing NV-Reason-CT Open 3D CT VLM for Radiologist Chain-of-Thought Reasoning

JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation

KwaiMind Technical Report

Less Is More in the Long Tail: Stage-Adaptive Sample Selection for Annotation-Efficient Dense Prediction

Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models

Mammo-LIFE: Longitudinal Mammographic Imaging and Clinical Feature Enrichment for Post-Radiotherapy Outcome Prediction

MedRSI: Recursive Self-Improvement for Medical Agents via Clinically Aligned Self-Evolution

Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes

Neoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic resonance imaging with clinical variables

Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models

StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement

TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum

Which small model works best with Ollama on a Raspberry Pi 5?

World In Your Hands: A Large-Scale and Open-Source Ecosystem for Learning Human-Centric Manipulation in the Wild

You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs

AniPrO: Interpretable Anime Image Provenance Detection via Multi-Dimensional Semantic Reasoning

Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images