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 177–192 of 567 proofs of work · Newest first
Page 12 of 36
implementationChecked Sep 22, 2026

Chatbot UI: An Open Source AI Chat Interface for Frontier Models

Mckay Wrigley · Takeoff / Chatbot UI

Architected Chatbot UI, a Next.js and Supabase open-source application with 30k+ stars enabling local and cloud deployment of multi-model chats, prompt presets, file uploads, and custom vector search embeddings.

Scope & limitations

Client-side state management requires persistent database sync for multi-device conversation state.

Context: OpenAI, Anthropic, Mistral, Ollama, pgvector embeddings.

View mission
explanationChecked Sep 22, 2026

ChatGPT and Healthcare: Clinical Applications and Diagnostic Augmentation

Dr. Harvey Castro · Healthcare AI Advisory

Authored the first medical reference manual for physicians examining generative AI utility in clinical note generation, patient triage, and medical education.

Scope & limitations

Generative LLMs must never replace primary clinical diagnostic reasoning without board-certified physician oversight.

Context: Clinical documentation, HIPAA data privacy, emergency medicine triage.

View mission
implementationChecked Sep 22, 2026

Cognosys: Autonomous Multi-Agent Web Execution Platform

Sulaiman Ghori · Cognosys

Engineered Cognosys, an autonomous agent execution environment that decomposes user goals into hierarchical subtasks, executes web browsing and code execution steps, and summarizes multi-step outcomes.

Scope & limitations

Recursive agent loops risk infinite token consumption without strict cycle detection and step budgets.

Context: GPT-4, Claude 3, isolated Docker sandboxes, LangChain orchestration, Supabase.

View mission
explanationChecked Sep 22, 2026

Collaborative Prompting: Conversational AI Workflows for Business Teams

Conor Grennan · NYU Stern / Generative AI

Formulated the 'collaborative prompting' methodology taught across NYU Stern executive programs, replacing static prompt templates with iterative dialogic steering.

Scope & limitations

Iterative prompting relies on user critical thinking to recognize and steer model assumptions.

Context: GPT-4o, Claude 3.5 Sonnet, iterative conversational prompting, business communication.

View mission
researchChecked Sep 22, 2026

Colorful Image Colorization with Deep Convolutional Neural Networks

Dr. Alexei Efros · UC Berkeley

Pioneered automated black-and-white image colorization by formulating the task as multinomial classification over quantized Lab color space with class rebalancing, tricking human observers into believing synthesized colors are real.

Scope & limitations

Ambiguous objects (e.g. clothing, cars) can display desaturated or sepia tints if the model averages multimodal color distributions.

Context: CIE Lab color space, class-rebalanced cross-entropy loss, 1.3M ImageNet images.

View mission
researchChecked Sep 22, 2026

Connectionist Temporal Classification: Labelling Unsegmented Sequence Data

Dr. Alex Graves · NNAISENSE / former Google DeepMind

Authored the monumental ICML 2006 paper introducing CTC loss, allowing RNNs to be trained directly on unsegmented, unaligned sequence pairs by integrating over all possible alignments with a blank token, with over 15,000 citations.

Scope & limitations

Assumes conditional independence between label outputs given the input sequence, necessitating external language models for grammar smoothing.

Context: Dynamic programming forward-backward algorithm, RNN sequence alignment.

View mission
researchChecked Sep 22, 2026

Contrastive Multiview Coding and Self-Supervised Representation Learning

Dr. Phillip Isola · MIT

Introduced Contrastive Multiview Coding (CMC), showing that maximizing mutual information across multiple views or sensory modalities learns invariant visual representations competitive with full ImageNet supervision.

Scope & limitations

Requires view-generation or multiple aligned cameras/modalities during pre-training to compute contrastive pairs.

Context: Multi-sensory embedding spaces, contrastive InfoNCE loss.

View mission
implementationChecked Sep 22, 2026

Copy.ai Workflows: Enterprise-Scale Autonomous GTM Engine

Paul Yacoubian · Copy.ai

Architected Copy.ai Workflows, an enterprise workflow automation engine executing millions of autonomous prospect research, content localization, and pipeline enrichment jobs with multi-model fallbacks.

Scope & limitations

High-volume web scraping dependencies are susceptible to IP blocking and dynamic website anti-bot protections.

Context: Multi-model orchestration: GPT-4o, Claude 3.5 Sonnet, Azure OpenAI, CRM APIs.

View mission
implementationChecked Sep 22, 2026

Crawl4AI: Open-Source LLM-Friendly Web Crawler and Extraction Engine

Minh Do · Crawl4AI

Designed and built Crawl4AI, a high-speed asynchronous web crawler that converts complex JavaScript-rendered web pages into clean, token-efficient Markdown formatted specifically for LLMs and RAG pipelines.

Scope & limitations

Aggressive anti-bot fingerprinting services (Cloudflare, Akamai) require proxy rotation.

Context: Playwright, AsyncIO, BeautifulSoup, LLM extraction schema, token minimization.

View mission
implementationChecked Sep 22, 2026

Cursor Rules and Autonomous AI Coding Harnesses

Dan Mindru · IndyDevDan / Independent AI Engineering

Created widely adopted open-source `.cursorrules` configurations and automated CLI developer scripts that enforce code conventions and automated test-driven development.

Scope & limitations

Rules must be scoped per subfolder in monorepos to avoid rule conflicts between frontend and backend.

Context: Cursor system instructions, Next.js, TypeScript, Vitest.

View mission
implementationChecked Sep 22, 2026

cvzone: Computer Vision Made Easy Open Source Library

Murtaza Hassan · Computer Vision Zone

Created cvzone, a widely used Python wrapper library with over 1M downloads simplifying OpenCV and MediaPipe integrations for hand tracking, facial mesh, and pose estimation.

Scope & limitations

MediaPipe hand landmarks require unhindered direct line of sight to camera sensor.

Context: MediaPipe, OpenCV, Python, real-time spatial coordinate calculation.

View mission
explanationChecked Sep 22, 2026

Data Science as a Service | Kumo AI Full Walkthrough

James Briggs · James Briggs AI / Vector Search Advisory

Authored technical video investigation comparing dense vector embeddings versus reciprocal rank fusion (RRF) with BM25 sparse vectors, demonstrating 28% improvement in Mean Reciprocal Rank (MRR).

Scope & limitations

Two-stage retrieval pipelines introduce 100-250ms of additional network latency for the reranking stage.

Context: Pinecone, Cohere Rerank, BM25, text-embedding-3-large, LangChain.

View mission
explanationChecked Sep 22, 2026

Decision Intelligence: The Unifying Framework for AI Strategy

Cassie Kozyrkov · Data Scientific

Formulated the foundational principles of Decision Intelligence, integrating managerial science, behavioral economics, and machine learning to improve executive AI decision-making.

Scope & limitations

Framework requires quantitative literacy across executive leadership teams.

Context: Decision intelligence, statistical hypothesis testing, AI error budgeting.

View mission
implementationChecked Sep 22, 2026

Deep Learning and Reinforcement Learning Project Blueprints

Nick Renotte · Nicholas Renotte Media

Maintains open-source code repositories with dozens of practical applied AI implementations, including real-time sign language detection and Mario reinforcement learning bots.

Scope & limitations

Deep reinforcement learning convergence requires millions of simulation steps and careful reward shaping.

Context: OpenAI Gym, Stable-Baselines3, PyTorch, OpenCV.

View mission
researchChecked Sep 22, 2026

Deep Speech: Scaling up End-to-End Speech Recognition

Dr. Awni Hannun · Apple Machine Learning Research

First author of the landmark Baidu Deep Speech paper, proving that replacing complex phonetic acoustic pipelines with a single recurrent neural network trained end-to-end with CTC achieves state-of-the-art accuracy in noisy real-world speech.

Scope & limitations

End-to-end recurrent models without attention mechanisms struggle to maintain alignment over multi-minute audio streams.

Context: Bidirectional RNNs, CTC loss, custom GPU parallel prefix beam search decoders.

View mission
Showing 177–192 of 567 proofs of work