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 305–320 of 567 proofs of work · Newest first
Page 20 of 36
explanationChecked Sep 22, 2026

Vibe Coding Case Studies: Shipping Enterprise Features with AI IDEs

Sahil Lavingia · Gumroad

Documented transparent, real-world case studies demonstrating how a single founder can write, test, and ship complete full-stack SaaS features to millions of users leveraging Cursor and Claude.

Scope & limitations

AI-assisted generation requires strict integration test suites to prevent regression bugs in business logic.

Context: Cursor AI, Claude 3.5 Sonnet, Ruby on Rails, Next.js, Postgres.

View mission
explanationChecked Sep 22, 2026

Voice First Architecture: Voice-to-Voice Real-Time Latency Foundations

Brian Roemmele · Voice First / Multiplex

Authored foundational papers predicting the convergence of conversational audio interfaces, local speech synthesis, and real-time streaming LLMs.

Scope & limitations

Full-duplex audio interruption handling requires sophisticated acoustic echo cancellation (AEC) at the hardware layer.

Context: Voice-to-voice streaming, sub-200ms latency, local speech tokens.

View mission
implementationChecked Sep 22, 2026

Voice-First Multimodal Agent Harnesses and Vibe Coding Workflows

Mckay Wrigley · Takeoff / Chatbot UI

Developed real-time voice agent prototypes combining WebSocket audio streaming, low-latency function calling, and Cursor-driven rapid software development workflows.

Scope & limitations

WebSocket audio streams are sensitive to network packet jitter and browser audio permissions.

Context: OpenAI Realtime API, Cursor AI code generation, ElevenLabs streaming audio.

View mission
implementationChecked Sep 22, 2026

Web Cafe AI Client Knowledge Base & Agent Templates

Corbin Brown · Web Cafe AI

Engineered reusable client delivery frameworks for syncing Notion, Google Drive, and Zendesk data into secure embedding indexes with role-based access control.

Scope & limitations

Incremental document sync requires webhook event listeners to capture upstream edits in real time.

Context: LangChain, ChromaDB, FastAPI, Next.js, Tailwind CSS.

View mission
explanationChecked Sep 22, 2026

What AI Researchers Saw, Before Their Demand to ‘Pace’ AI

Michael Spencer · AI Explained

Conducted independent empirical benchmarking evaluating reasoning saturation on GPQA, ARC-AGI, and SWE-bench, identifying degradation patterns in extended context retrieval.

Scope & limitations

Public benchmarks risk subtle test-set contamination in subsequent foundation model training rounds.

Context: GPT-4o, Claude 3.5 Sonnet, o1-preview, SWE-bench Verified, ARC-AGI.

View mission
explanationChecked Sep 22, 2026

Wisdom Keepers and Decentralized Local Offline Intelligence

Brian Roemmele · Voice First / Multiplex

Researched hardware and memory architectures for storing complete cultural, historical, and technical knowledge bases on offline non-volatile solid state media.

Scope & limitations

Offline models cannot retrieve real-time post-cutoff information without local sensor telemetry.

Context: Compressed quantized weights, offline embedding indexes, edge hardware.

View mission
implementationChecked Sep 22, 2026

Writing An Interpreter and Compiler In Go

Thorsten Ball · Independent Author & Systems Engineer

Authored two landmark engineering books used by university curricula and tens of thousands of systems engineers worldwide to learn lexing, parsing, AST generation, and bytecode virtual machines.

Scope & limitations

Focuses on language implementation theory rather than modern JIT compiler optimizations.

Context: Go, lexer/parser construction, tree-walking interpreters, bytecode compilers.

View mission
explanationChecked Sep 22, 2026

Yes, Jev Is Insane, But There's A Catch

Dr. Károly Zsolnai-Fehér · Two Minute Papers / TU Wien

Synthesized cutting-edge neural rendering, 3D Gaussian splatting, and embodied robotics research into structured visual explainers educating over 1.6 million researchers and engineers.

Scope & limitations

High-level visual summaries omit raw mathematical proof derivations found in primary conference preprints.

Context: NeRF, 3D Gaussian Splatting, physics-based neural simulation, Sora diffusion.

View mission
researchChecked Sep 21, 2026

Accurate Structure Prediction of Biomolecular Interactions with AlphaFold 3

Dr. John Jumper · Google DeepMind

Co-led AlphaFold 3 research in Nature 2024, replacing Evoformer representations with a Diffusion Module to predict joint structures of proteins, nucleic acids (DNA/RNA), post-translational modifications, and small-molecule drugs.

Scope & limitations

Drug binding pocket predictions require experimental crystallization or binding assays for clinical drug validation.

Context: Pairformer architecture coupled with a 3D coordinate diffusion denoising module.

View mission
implementationChecked Sep 21, 2026

AlphaFold 2: Computational Structural Biology Prediction Engine Across 200M+ Proteins

Dr. John Jumper · Google DeepMind

First author and technical architect of the open-source AlphaFold 2 computational system, predicting 3D coordinates of all cataloged proteins in the UniProt database with atomic precision.

Scope & limitations

Computational requirements for long sequence complexes (>2000 residues) require high-memory GPUs (A100/H100).

Context: JAX/Haiku, Multiple Sequence Alignment (MSA) representations, structural recycling iterations.

View mission
researchChecked Sep 21, 2026

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration

Dr. Song Han · MIT / HAN Lab

Published the MLSys Best Paper proving that protecting the top 1% of salient weight channels based on activation magnitudes enables hardware-friendly 4-bit weight-only quantization without costly backpropagation or retraining.

Scope & limitations

Requires representative calibration datasets to accurately identify activation outliers across specialized domains.

Context: 4-bit integer weights, FP16 activations, evaluated across LLaMA-1/2, Vicuna, StarCoder.

View mission
researchChecked Sep 21, 2026

Aya: An Open Multilingual Foundation Model and Evaluation Dataset for 101 Languages

Dr. Sarah Hooker · Cohere For AI

Directed the global Aya research collaboration involving 3,000+ researchers across 119 countries to produce instruction datasets and state-of-the-art open-weights multilingual foundation models for underrepresented languages.

Scope & limitations

Extremely low-resource languages with minimal digital footprint require specialized human annotation to avoid hallucination.

Context: Cohere Command base weights, 101 languages, 513M human-curated multilingual instruction tokens.

View mission
researchChecked Sep 21, 2026

Classifier-Free Diffusion Guidance (CFG)

Dr. Jonathan Ho · Independent / ex-OpenAI

Invented Classifier-Free Guidance (CFG), a mathematical formulation that jointly trains conditional and unconditional diffusion models, dramatically improving prompt fidelity without requiring separate classifier gradients.

Scope & limitations

High guidance scales cause over-saturation and high-frequency pixel artifacts without dynamic thresholding.

Context: Conditioning dropout during training, weighted score extrapolation during inference sampling.

View mission
implementationChecked Sep 21, 2026

Cursor Speculative Code Editing & Shadow Workspace Architecture

Aman Sanger · Cursor / Anysphere

Architected Cursor's instant-apply and speculative editing engine, which runs isolated shadow syntax trees to predict multi-token keystrokes and merge large diffs into production codebases with zero visual latency.

Scope & limitations

Requires real-time AST parsing and language server protocol (LSP) indexing to ensure semantic validity of speculative edits.

Context: Custom fine-tuned small speculative draft models paired with frontier reasoning models (Claude 3.5 Sonnet, GPT-4o).

View mission
researchChecked Sep 21, 2026

Deep Residual Learning for Image Recognition (ResNet)

Dr. Kaiming He · MIT EECS

First author of the CVPR 2016 Best Paper introducing identity skip connections (Residual Networks), overcoming vanishing gradients to train 100+ layer networks, which became standard across all modern deep learning and transformers.

Scope & limitations

Pure convolutional ResNets possess localized receptive fields, necessitating hybrid attention blocks for global context modeling.

Context: Skip connections (x + F(x)), Batch Normalization, ResNet-50/101/152 architectures.

View mission
researchChecked Sep 21, 2026

Denoising Diffusion Probabilistic Models (DDPM)

Dr. Jonathan Ho · Independent / ex-OpenAI

First author of the groundbreaking NeurIPS 2020 paper that demonstrated diffusion models could surpass GANs and autoregressive models in generative image fidelity via variational bound simplification.

Scope & limitations

Standard DDPM required hundreds of sequential sampling steps, requiring modern ODE solvers or flow matching for real-time speed.

Context: Gaussian forward diffusion schedule, reverse Markov chain denoising score matching, U-Net architecture.

View mission
Showing 305–320 of 567 proofs of work