AI Wiki — Knowledge Base

Hi everyone, I'm building a local AI agent with Ollama and exploring dynamic PDF extraction. Since Ollama can't directly process PDFs, I'm extracting text and passing it via prompts. Should I use PDFPlumber, a vector database (RAG), or another approach for accurate document understanding? Guide me !

User seeks guidance on PDF processing methods for local AI agents built with Ollama, comparing approaches like PDFPlumber extraction, vector database RAG systems, and alternative techniques for accura

local-air-ollama

8 Jun 2026

Search: “evaluation”

Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems

Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation

Detecting Temporally Localized Manipulations in Authentic Video Streams

Didact: A Cross-Domain Capability Discovery System for Defence

Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking

Does Topic Sentiment Cause Perceived Ideology? Comparing Human and LLM Annotations in Political News Articles

DSU-Net: An Attention-Enhanced Dense Skip U-Net for Breast Lesion Segmentation in Mammographic Images

EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure Estimation

Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation

Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection

Explicit Evidence Grounding via Structured Inline Citation Generation

Extending Responsibility-Sensitive Safety for the Assessment of Offloaded Autonomous Driving Services

FIGMA: Towards FIne-Grained Music retrievAl

From Vision to Text: A Compact Multimodal Approach for Robust, Cross-Domain Presentation Attack Detection on ID Cards

Generative Models Erode Human Temporal Learning Through Market Selection

GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution

GS-KAN: Parameter-Efficient Kolmogorov-Arnold Networks via Sprecher-Type Shared Basis Functions

GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding

Hermes: Accelerating Long-Latency Load Requests via Perceptron-Based Off-Chip Load Prediction

HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule

HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG

How reliable are LLMs when it comes to playing dice?

I really do think we'll see a lot of value accrue in AI startups building 'model routing as a service' Not just OpenRouter - this includes a…

Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios

Learn to Match: Two-Sided Matching with Temporally Extended Feedback

Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes

Lighting-Aware Representation Learning under Controllable Lighting Variation

LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G

LLM-Guided Search for Deletion-Correcting Codes

LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling

Machine Learning for Electron-Scale Turbulence Modeling in W7-X

MatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models

Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations

Mission-Level Runtime Assurance Framework for Autonomous Driving

MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs

Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks

Modular Monolingual Adaptation using Pretrained Language Models

MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection

Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA

Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials

NTILC: Neural Tool Invocation via Learned Compression

OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation

On the Effect of Neural Field Reparameterization for 4DVAR

One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models

Online Pandora's Box for Contextual LLM Cascading

OpenACMv2: An Accuracy-Constrained Co-Optimization Framework for Approximate DCiM

OpenGlass: Open-Source Smart Glasses for On-Device Event-Based Gesture Recognition