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: “models”

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work…

ZIPBrain: Can EEG Foundation Models Be Faster, Locally Deployable, but Accurate?

OpenAI reveals upcoming Astra model may possess ‘critical’ hacking capabilities

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

DynaPix: Can Vision-Language Models Identify the Exact Future?

Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction

GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions

Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations

An accurate characterization of the arc of AI is that it is shaped by two trends: 1. Moving more and more logic to a neural model for tasks …

CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models

HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language 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

LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling

Mamba with Hierarchical Memory: Solving Representation Bottleneck in Long Sequence Modeling

Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?

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

A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

A game theory for foundation models shows new paths to rational cooperation through similarity inference

Can Text-to-Image Models Draw from the Right Frame of Reference?

Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models

Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili

dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model

HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection

LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation

MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models

MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding

Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models

SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay

SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling

A Heuristic Perspective on Debiasing Language Models

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models

Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data

Cluster-Aware Over-the-Air Federated Learning with Energy-Harvesting Devices: From Global Training to Model Personalization

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

I benchmarked the 4 models I had pulled. The 1.1GB one beat the 2GB one at math and lost badly at extraction.

Learning the Pareto Frontier of Predictive Models under Distribution Shift

Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models

MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models

Mistral releases Shieldstral, a 3B multimodal safety classifier that it says matches models up to 7x its size on text safety, available under Apache 2.0 (Mistral AI Blog)

MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling

Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams

PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs

Progressive^2: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression

Releasing Pokee-Isaac 28B — the world’s first real 10M-token context frontier-class agentic model, deployable on a single GPU (starting from…