AI Wiki — Knowledge Base

i just spent weeks rewriting my webUI from scratch, getting rid of all AI slop within the codebase and switching it over to a proper lightweight framework (alpine.js). i am now comfortable suggesting it as an alternative to openwebUI, librechat and the like! it is made for local models

[Fully open source under GPL3, made from the ground up for use with local models, no subscriptions, no corporate backing] When i first started this, it was meant to be a fully lightweight, extremely m

local-air-localllama

6 Aug 2026

Search: “inference”

Galaxy Phase-Space and Field-Level Cosmology: The Strength of Semi-Analytic Models

General Availability of Pinecone Nexus Proves Knowledge Drives Real Outcomes for Agentic AI

Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent

HelloWorld: Enabling Socially Interactive Characters in Video World Models

i just spent weeks rewriting my webUI from scratch, getting rid of all AI slop within the codebase and switching it over to a proper lightweight framework (alpine.js). i am now comfortable suggesting it as an alternative to openwebUI, librechat and the like! it is made for local models

Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent

Item Response Theory for AI Safety

Large-Small Model Collaboration for Enhancing Edge-Deployed Small Models

LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching

MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight

MVTOP: Multi-View Transformer-based Object Pose-Estimation

Neighborhood-Aware Dual Biomedical Entity Linking

NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment

PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images

Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion

Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes

PRIMAL3: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Leveraging LaCAM3

Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning

Reconstructing Persistent Worlds from Narratives for Narrative-Grounded Interactive Experiences

RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care

Retrieve in Time, Correct in Frequency

Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition

Robust Control under Stationary Ambiguity

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction

Semantic Frame Interpolation

SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization

SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding

Teaching Foundation Models to Read mmWave: Pose-Guided Kinematic Representation for Human Behavior Understanding

The Yokai Learning Environment: Tracking Beliefs Over Space and Time

Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision

Unifying quantum measurement constructions via a relative-entropy minimum change principle

When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning

A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces

Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation

Agent memory layers don't need an LLM deciding what to remember

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding

Amortized Interventional Forecasting for Multivariate CIR Processes

Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering

BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems

Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms

Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety

Bimanual Manipulation Within an 8 GB Budget: Zero-Copy Sensing and Quantized ACT on an Entry-Level Jetson

Calibrating Semantic Uncertainty from Observable Language-Model Probabilities

CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting

Consensus Measures for Unstructured Biomedical Text Annotations

Deep Frequency-Aware Functional Maps for Robust Shape Matching