PUBLISHED AI RESEARCH AND PROJECTS

AI research and projects

The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.

A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗

Showing 145–160 of 567 proofs of work · Newest first
Page 10 of 36
explanationChecked Sep 23, 2026

The PARE Prompt Architecture for Complex Business Analytics

Christopher S. Penn · Trust Insights

Engineered the PARE framework (Prime, Augment, Refresh, Evaluate) to systematically eliminate model drift and hallucination during multi-step financial and marketing reporting over raw tabular data.

Scope & limitations

Requires structured schema validation on source tabular inputs prior to prompt passing.

Context: Code Interpreter / Advanced Data Analysis environments, Python execution sandboxes, Claude Artifacts.

View mission
explanationChecked Sep 23, 2026

The Zero-Marginal-Cost Startup: Scaling Ventures with AI Leverage

Matt Higgins · RSE Ventures

Keynote curriculum demonstrating how venture-backed startups utilize small multi-disciplinary teams coupled with autonomous agent stacks to achieve $10M+ ARR milestones without linear headcount expansion.

Scope & limitations

Requires high managerial discipline to prevent tool sprawl and maintain clean data architecture.

Context: Venture scale economics, executive automation stacks, lean operational scaling.

View mission
implementationChecked Sep 23, 2026

Virtual Brand Persona Protection & AI Licensing Standard

Cathy Hackl · Spatial Dynamics

Authored enterprise guidelines establishing commercial IP licensing boundaries for synthetic digital likenesses and conversational executive avatars used in marketing campaigns.

Scope & limitations

Legal precedents across international jurisdictions remain fragmented and evolving.

Context: Digital rights management, synthetic voice contracts, likeness clearance protocols.

View mission
implementationChecked Sep 23, 2026

Voice Cloning & AI Avatar Synthesis for Executive Personal Branding

Salma Jafri · Salma Jafri Media

Tested and documented best-practice guardrails for executives using cloned voices and generative video avatars to maintain genuine personal connection without uncanny valley artifacts or audience alienation.

Scope & limitations

Avatars require clear on-screen transparency disclaimers to maintain audience trust.

Context: HeyGen video avatars, ElevenLabs professional voice clone, ethical disclosure protocols.

View mission
explanationChecked Sep 22, 2026

A day in the life an ML engineer 2 (filtering data, training small models, building apps, walking)

Daniel Bourke · Nutrio / Independent AI Engineer

Authored and recorded the 25-hour open-access PyTorch curriculum covering tensors, neural networks, computer vision, transfer learning, and model deployment.

Scope & limitations

Focuses on foundational vision and classification rather than distributed pre-training of 70B+ LLMs.

Context: PyTorch 2.x, TorchVision, CUDA, transfer learning with EfficientNet and ViT.

View mission
researchChecked Sep 22, 2026

A Foundation Model for Clinician-Centered Drug Repurposing with TxGNN

Dr. Kexin Huang · Stanford University / Harvard University

First author of the Nature Medicine 2024 paper introducing TxGNN, a geometric foundation model trained on a medical knowledge graph of 17,080 diseases to identify drug repurposing opportunities for rare diseases with clinician-interpretable rationales.

Scope & limitations

Predictions require in vitro wet-lab assay validation and clinical trials before therapeutic efficacy can be established.

Context: Graph Neural Networks, 17k disease knowledge graph, clinician explanatory subgraphs.

View mission
explanationChecked Sep 22, 2026

AdCar is the digital and physical Ad Space for Startups & Small Brands

Dan Mindru · IndyDevDan / Independent AI Engineering

Technical guide demonstrating how to build, test, and connect custom Model Context Protocol (MCP) servers in TypeScript to give Cursor and Claude desktop direct database and filesystem access.

Scope & limitations

MCP servers require strict local sandboxing to prevent agent-initiated unintended destructive system commands.

Context: Model Context Protocol (MCP), TypeScript, Cursor, Claude 3.5 Sonnet.

View mission
implementationChecked Sep 22, 2026

Agentic AI Developer Tools and TypeScript Ecosystem Libraries

Travis Fischer · Automated / Open Source

Created and maintains dozens of open-source TypeScript packages with millions of monthly downloads, including headless browser utilities and AI SDK wrappers used across leading web applications.

Scope & limitations

Maintaining third-party reverse-engineered APIs requires constant updates when upstream web services modify their undocumented schemas.

Context: TypeScript, Node.js, Vercel AI SDK, OpenAI API, Anthropic API.

View mission
implementationChecked Sep 22, 2026

Agentic Memory Systems and Cognitive Graph Blueprints

Harrison Kinsley · sentdex / NNFS

Created open-source Python implementations of dynamic knowledge graph generation and stateful memory reflection for autonomous research agents.

Scope & limitations

Graph schema extraction from unstructured text can generate redundant edge relations without entity reconciliation.

Context: Python, NetworkX, Neo4j, LlamaIndex, OpenAI API.

View mission
researchChecked Sep 22, 2026

Aggregated Residual Transformations for Deep Neural Networks (ResNeXt)

Dr. Saining Xie · New York University (NYU)

Co-authored the seminal CVPR 2017 paper introducing ResNeXt, which introduced 'cardinality' (the size of the set of transformations) as a concrete, essential dimension that outclasses depth and width for computer vision accuracy.

Scope & limitations

Grouped convolution memory access patterns can yield lower tensor-core utilization compared to standard dense GEMMs.

Context: Grouped convolutions, split-transform-merge topology, ImageNet-1k classification.

View mission
explanationChecked Sep 22, 2026

AI labs may be hiding their biggest breakthroughs

Wes Roth · Wes Roth Media / Applied AI Insights

Produced an exhaustive structural analysis of reinforcement learning scaling laws, test-time compute scaling, Multi-Head Latent Attention (MLA), and inference cost reductions.

Scope & limitations

Inference economics depend heavily on hardware deployment profiles and FP8 quantization efficiency.

Context: DeepSeek-R1, OpenAI o1, test-time compute scaling, GRPO training dynamics.

View mission
explanationChecked Sep 22, 2026

AI News: The AI Slowdown: What You Need to Know

Matt Wolfe · FutureTools / Matt Wolfe Media

Published dozens of rigorous comparative video investigations evaluating AutoGPT, CrewAI, local Ollama execution, and video generation models with repeatable real-world tasks.

Scope & limitations

Evaluations reflect snapshot model checkpoints that may change with silent cloud provider updates.

Context: Local LLMs, ComfyUI, Runway Gen-3, Midjourney, AutoGPT, CrewAI.

View mission
explanationChecked Sep 22, 2026

AI Product Management Frameworks and Evaluation Rubrics

Aakash Gupta · Product Growth / Independent Advisory

Formulated the foundational operational frameworks for AI PMs, detailing how to manage stochastic failure states, set confidence thresholds, and instrument telemetry for generative features.

Scope & limitations

Frameworks must be adapted when transitioning from deterministic classification to unstructured creative generation.

Context: Human-in-the-loop UX, confidence score routing, telemetry instrumentations.

View mission
explanationChecked Sep 22, 2026

AI4Diversity: Global Frameworks for Ethical and Inclusive AI Models

Steve Nouri · AI4Diversity / Generative AI

Led international community initiatives uniting 100,000+ practitioners to establish open audit standards for algorithmic fairness, demographic parity, and cultural representation in LLMs.

Scope & limitations

Cultural fairness benchmarks vary widely across international jurisdictions and local idioms.

Context: Algorithmic bias detection, fairness metrics, multilingual evaluation datasets.

View mission
explanationChecked Sep 22, 2026

An ex-OpenAI researcher just deleted language from the LLM...

Jeff Delaney · Fireship.io

Analyzed the shift from manual coding to conversational, prompt-guided software engineering using Cursor, Claude 3.5 Sonnet, and Copilot, demonstrating rapid full-stack application synthesis.

Scope & limitations

AI-first vibe coding requires developer intuition to catch security vulnerabilities and silent edge-case logic failures.

Context: Cursor AI, Claude 3.5 Sonnet, Next.js, Supabase, Tailwind CSS.

View mission
implementationChecked Sep 22, 2026

Ask-My-PDF and Enterprise Chatbot Repositories

Alejandro AO · Alejandro AO AI Engineering

Authored open-source repositories with thousands of stars demonstrating end-to-end full-stack PDF retrieval chat interfaces using Streamlit, FastAPI, and LangChain.

Scope & limitations

In-memory vector indexing with FAISS is bounded by container RAM on multi-gigabyte document sets.

Context: Python, PyPDF, Streamlit, LangChain, FAISS local vector store.

View mission
Showing 145–160 of 567 proofs of work