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 545–560 of 567 proofs of work · Newest first
Page 35 of 36
researchChecked Sep 20, 2026

Deep Medicine: High-Performance AI in Clinical Diagnostics and Patient Care

Dr. Eric Topol · Scripps Research

Clinical evaluation assessing the diagnostic accuracy, speed, and safety boundaries of multimodal AI models across cardiology, radiology, and oncology.

Scope & limitations

Clinical diagnostic deployment requires FDA approval and institutional ethics review; model outputs must assist rather than replace licensed physician judgment.

Context: Multimodal clinical models, ECG neural nets, and electronic health record parsing.

View mission
researchChecked Sep 20, 2026

Large-Scale Generative AI Red-Teaming Methodology

Dr. Rumman Chowdhury · Humane Intelligence

Community red-teaming protocols orchestrating thousands of independent researchers to evaluate bias, safety boundaries, and prompt exploits in commercial foundation models.

Scope & limitations

Evaluates public checkpoint behavior; closed proprietary internal corporate systems require continuous telemetry auditing.

Context: Adversarial prompt evaluation and bias detection metrics.

View mission
explanationChecked Sep 20, 2026

Patterns for Building LLM-based Systems & Products

Eugene Yan · Amazon

Comprehensive reference manual documenting production patterns for evaluation, guardrails, retrieval-augmented generation, and fine-tuning with cost/latency trade-offs.

Scope & limitations

System design patterns; individual implementations must be profiled for specific latency constraints.

Context: Python, vector indexes, cross-encoders, and LLM evaluation frameworks.

View mission
explanationChecked Sep 20, 2026

The AI Engineer: The Rise of the Fastest Growing Role in Software Engineering

Swyx (Shawn Wang) · Smol.ai / Latent Space

Seminal technical essay analyzing the shift from classical ML research to application-layer AI engineering, defining evaluation, prompt caching, reasoning scaffolding, and tool integration.

Scope & limitations

Framework assumes APIs and open weights continue advancing capabilities faster than traditional specialized training.

Context: Foundation model APIs, TypeScript, Python, and developer tooling.

View mission
explanationChecked Sep 20, 2026

LLM-Powered Autonomous Agents: Comprehensive System Design & Architecture Analysis

Dr. Lilian Weng · Independent / ex-OpenAI

Landmark reference architecture decomposing autonomous agents into planning (subgoal decomposition, reflection), memory (short-term in-context, long-term vector search), and tool execution loops.

Scope & limitations

Identifies fundamental limits of finite context windows, reliability bottlenecks in long-term planning, and unreliability of open-ended natural language tool interfaces.

Context: Large language models, vector memory systems, ReAct prompting, and agent loops.

View mission
researchChecked Sep 20, 2026

Abu Dhabi Investment Authority (ADIA): Domain-Specific AI Evaluation Benchmark & Methodology

Dr. Marcos Lopez de Prado · Abu Dhabi Investment Authority (ADIA)

An empirical evaluation methodology developed by Dr. Marcos Lopez de Prado at Abu Dhabi Investment Authority (ADIA), establishing standardized performance metrics, domain-specific evaluation sets, and error taxonomy protocols.

Scope & limitations

Evaluation benchmark protocol; empirical accuracy reflects specific test distributions and requires periodic refresh.

Context: Mathematical finance, combinatorial cross-validation, and portfolio optimization.

View mission
implementationChecked Sep 20, 2026

pH-7 Open-Source Web Framework Architecture & AI-Integrated Software Suite

Pierre-Henry Soria · Soria / pH-7

Public open-source software suite implementing modular OOP architecture, test-driven development (TDD), and extensible AI microservices with over a decade of production maintenance.

Scope & limitations

Requires modern PHP 8.2+ or Node.js runtime environments with relational database backends (PostgreSQL, MySQL).

Context: Open-source GitHub repository with automated CI/CD test suites, static analysis, and Docker configurations

View mission
researchChecked Sep 20, 2026

Voyager: An Open-Ended Embodied Agent with Large Language Models

Dr. Jim Fan · NVIDIA

Lifelong learning autonomous agent architecture featuring an automated curriculum, self-expanding skill library of executable code, and iterative prompting mechanism with environment feedback.

Scope & limitations

Dependent on real-time vision-language reasoning latency; physical embodiment requires sim-to-real transfer validation.

Context: GPT-4, Mineflayer JavaScript bot API, vector database skill retriever, and Python.

View mission
researchChecked Sep 20, 2026

Voyager: An Open-Ended Embodied Agent with Large Language Models

Dr. Linxi (Jim) Fan · NVIDIA

Groundbreaking research introducing Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores world dynamics, acquires skills, and makes novel discoveries without human intervention.

Scope & limitations

Evaluated within Minecraft simulation environment; real-world robotic embodiment introduces hardware physical latencies and physical sensor noise.

Context: GPT-4 prompting, iterative prompting mechanism, and skill library retrieval.

View mission
implementationChecked Sep 20, 2026

bitsandbytes: 8-Bit and 4-Bit CUDA Quantization Primitives

Tim Dettmers · Allen Institute for AI (Ai2)

The open-source library behind 8-bit matrix multiplication and 4-bit NormalFloat quantization, enabling consumer GPUs to run and train 70B+ parameter foundation models with negligible accuracy loss.

Scope & limitations

Tightly coupled with NVIDIA CUDA architectures; requires compilation of custom C++/CUDA kernels for optimal memory coalescing.

Context: CUDA, C++, Python, Hugging Face transformers, PEFT, and PyTorch.

View mission
explanationChecked Sep 20, 2026

Building LLM-Based Systems: Latency, Cost, and Architecture Trade-offs

Chip Huyen · Independent / Claypot AI

Comprehensive guide detailing the engineering differences between training, fine-tuning, and prompt-based RAG architectures in enterprise production.

Scope & limitations

System design blueprint; implementation performance depends on team infrastructure and latency budgets.

Context: LLM systems engineering, inference caching, and evaluation harnesses.

View mission
implementationChecked Sep 20, 2026

BabyCatAGI: Parallel Task Execution and Priority Orchestration Engine

Yohei Nakajima · Untapped VC

An advanced iteration of the autonomous BabyAGI architecture created by Yohei Nakajima, introducing parallel agent threads, dynamic task prioritization, and structured context sharing.

Scope & limitations

Autonomous agent loops can recurse indefinitely without strict budget stop conditions; relies on foundation model task completion signals.

Context: Python, Chroma/Pinecone vector storage, and OpenAI API.

View mission
implementationChecked Sep 20, 2026

Guardrails: Adding Guardrails to Large Language Models with Structured Validation

Shreya Rajpal · Guardrails AI

An open-source specification language (RAIL) and runtime engine enforcing structure, type, and semantic quality constraints on LLM outputs with automated corrective re-asking loops.

Scope & limitations

Corrective re-asking loops introduce additional inference latency and token overhead on malformed generations.

Context: Python, Pydantic, JSON Schema validation, and multi-model LLM APIs.

View mission
implementationChecked Sep 20, 2026

PyHealth: A Deep Learning Toolkit for Healthcare AI and Clinical Predictive Modeling

Dr. Jimeng Sun · University of Illinois Urbana-Champaign (UIUC)

Modular PyTorch toolkit standardizing clinical machine learning workflows across MIMIC, eICU, and OMOP datasets for mortality prediction, readmission risk, and drug recommendation.

Scope & limitations

Requires HIPAA-compliant data environments and de-identification pipelines when handling raw electronic health records.

Context: PyTorch, Python, OMOP Common Data Model, MIMIC-IV, and clinical embeddings.

View mission
implementationChecked Sep 20, 2026

nanoGPT: Minimal, Readable, and Fast PyTorch Framework for Training Medium GPTs

Andrej Karpathy · Eureka Labs / ex-Tesla, OpenAI

A pure, clean, and hackable 300-line PyTorch implementation for training, fine-tuning, and evaluating transformer language models with support for FlashAttention and torch.compile.

Scope & limitations

Engineered for educational transparency and small-to-medium parameter models; multi-node distributed trillion-token training requires complex pipeline parallel frameworks like Megatron.

Context: PyTorch 2.0, CUDA, Python, FlashAttention, and OpenWebText.

View mission
Showing 545–560 of 567 proofs of work