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.

Clear all filters

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

Showing 145–160 of 241 proofs of work · Kind: implementation · Newest first
Page 10 of 16
implementationChecked Sep 20, 2026

High-Speed Optical Character Recognition and Table Extraction Engine

Daniil Komov · SentiSight.ai / Neurotechnology

Developed an end-to-end OCR and table structure recognition engine capable of processing warped or skewed scans at under 100ms per page with 98.7% character accuracy across Latin and Cyrillic scripts.

Scope & limitations

Heavily degraded handwritten documents require specialized handwriting transformer (HTR) checkpoints.

Context: Convolutional recurrent neural network (CRNN) with CTC loss, line segmentation heuristics.

View mission
implementationChecked Sep 20, 2026

Self-Healing Kubernetes CI/CD Pipeline with AI Log Anomaly Detection

Michael Ballard · Slashdev

Engineered an automated observability pipeline that ingests Kubernetes container logs, flags runtime memory spikes or deadlocks, and automatically recommends or executes configuration rollbacks.

Scope & limitations

High false-alarm rates during deliberate rolling updates require suppression windows during planned maintenance deployments.

Context: Prometheus, Grafana Loki, Mistral-7B-Instruct fine-tune for root cause analysis.

View mission
implementationChecked Sep 20, 2026

Web-Based Deep Learning Model Training and Annotation Platform

Daniil Komov · SentiSight.ai / Neurotechnology

Architected a cloud-based platform enabling non-technical users to annotate images with bounding boxes, polygons, and keypoints, and train custom classification, object detection, and OCR models with one click.

Scope & limitations

Training speed depends on GPU cluster queue availability during peak multi-user training workloads.

Context: PyTorch, ONNX Runtime, WebSockets for live training metrics, automated augmentations.

View mission
implementationChecked Sep 20, 2026

Cohere Command R+ Enterprise Agentic Retrieval & Tool Calling Engine

Aidan Gomez · Cohere

Directed the development of Command R+, an open-weights 104B parameter model optimized specifically for multi-step agentic workflows, multi-lingual enterprise Retrieval-Augmented Generation (RAG), and cited tool calling across complex relational schemas.

Scope & limitations

Heavy memory footprint requiring 4x NVIDIA A100 (80GB) or quantized 8-bit / 4-bit deployments in production environments.

Context: 104B parameters, 128k context window, native citation grounding, multi-turn tool use API schema.

View mission
implementationChecked Sep 20, 2026

DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines

Dr. Matei Zaharia · Databricks / UC Berkeley

Co-created DSPy, a programming framework that abstracts brittle prompt engineering into typed declarative modules (Predict, ChainOfThought, ProgramOfThought) and uses optimizers (BootstrapFewShot, MIPRO) to compile optimal few-shot prompts and weight updates automatically.

Scope & limitations

Compiling complex multi-step pipelines requires running multiple optimization iterations, incurring upfront LLM invocation tokens during the optimization phase.

Context: Python 3.10+, automated LLM teleprompter evaluation harnesses, supports local vLLM and remote API providers.

View mission
implementationChecked Sep 20, 2026

Enterprise AI Chatbot Architecture with Multi-Tenant RBAC

Rahul Patel · Space-O Technologies / ManageMyClaw

Architected a multi-tenant enterprise knowledge base system supporting enterprise role-based access control (RBAC), ensuring sensitive corporate documents are retrievable only by authorized employee access tiers.

Scope & limitations

Large document corpora require periodic vector re-indexing when permission ACLs are updated dynamically in Active Directory.

Context: LangChain, Pinecone vector database, Azure OpenAI Service, OAuth 2.0 / SAML integration.

View mission
implementationChecked Sep 20, 2026

Enterprise LLM Guardrail and PII Anonymization Middleware

Helena García Borrella · The Interactive Studio / Codebridge Tech

Built a low-latency proxy middleware that detects and redacts GDPR-regulated personally identifiable information (PII) before queries are routed to public foundation model APIs.

Scope & limitations

Highly domain-specific acronyms can trigger false positive redactions unless explicitly whitelisted in custom dictionary sets.

Context: Microsoft Presidio, spaCy Spanish/English NER models, Redis cache layer.

View mission
implementationChecked Sep 20, 2026

High-Concurrency Web Scraping and Vector Ingestion Pipeline

Raúl Pineda Mejía · Codebridge Tech / The Interactive Studio

Built an asynchronous distributed scraping pipeline using headless browsers and vector databases that processes 50,000 corporate pages daily, generating semantic chunks and indexing them into Qdrant for semantic search.

Scope & limitations

Dynamic anti-bot protections require continuous proxy rotation and rate limit backoff strategies.

Context: Node.js, Puppeteer, Qdrant vector database, OpenAI text-embedding-3-small.

View mission
implementationChecked Sep 20, 2026

Hugging Face Transformers Platform & Open Weights Ecosystem

Clem Delangue · Hugging Face

Co-created and scaled the Hugging Face platform, which provides standardized APIs and model abstractions for PyTorch, TensorFlow, and JAX across hundreds of thousands of state-of-the-art transformer checkpoints.

Scope & limitations

Coordinating hundreds of diverse community model architectures requires continuous backwards-compatibility testing across rapidly evolving PyTorch versions.

Context: PyTorch, SafeTensors, ONNX, vLLM, DeepSpeed, BitsAndBytes quantization backends.

View mission
implementationChecked Sep 20, 2026

Mistral 7B: Grouped-Query and Sliding Window Attention Foundation Model

Arthur Mensch · Mistral AI

Designed and published Mistral 7B, an open-weights autoregressive transformer utilizing Grouped-query Attention (GQA) and Sliding Window Attention (SWA) to achieve faster inference and handle 8k context sequences while beating Llama 2 13B across all standard benchmarks.

Scope & limitations

Requires high cache memory bandwidth on commodity GPUs; sliding window attention drops exact attention history beyond context horizon without caching adaptations.

Context: 7.3B parameters, 32 layers, hidden dimension 4096, 32 attention heads, 8 key-value heads (GQA), sliding window attention of 4096 tokens.

View mission
implementationChecked Sep 20, 2026

MLflow: A Machine Learning Lifecycle and Foundation Model Evaluation Platform

Dr. Matei Zaharia · Databricks / UC Berkeley

Created MLflow, an open-source platform managing the end-to-end machine learning lifecycle, including experiment tracking, model registry, artifact packaging, and evaluation metrics for classical ML and modern LLM pipelines.

Scope & limitations

Self-hosted deployments require configuring and maintaining persistent artifact object storage (S3/GCS) and relational backend metadata databases.

Context: Python, REST, Docker packaging, native support for PyTorch, Hugging Face, LangChain, and OpenAI SDKs.

View mission
implementationChecked Sep 20, 2026

Multi-Agent Workflow Orchestration for Financial Document Processing

Helena García Borrella · The Interactive Studio / Codebridge Tech

Designed and deployed an autonomous multi-agent pipeline parsing heterogeneous multilingual financial invoices, extracting line items into structured JSON, and verifying tax calculations with zero human intervention.

Scope & limitations

Invoices with non-standard European VAT layouts require automated human-in-the-loop review queues.

Context: GPT-4o-mini, LangGraph, Pydantic validation schemas, OCR vision models.

View mission
implementationChecked Sep 20, 2026

Needle In A Haystack: Pressure Testing Long Context Retrieval in LLMs

Greg Kamradt · Data Independent

Created the industry-standard Needle In A Haystack benchmark that places distinct target facts across varying depths (0% to 100%) and context lengths (1k to 1M+ tokens) to measure retrieval degradation in frontier foundation models.

Scope & limitations

Single-needle retrieval does not test complex multi-hop reasoning or distributed cross-document synthesis across long contexts.

Context: Evaluated across GPT-4-Turbo, Claude 2.1/3, Gemini 1.5 Pro, Llama-3-70B.

View mission
implementationChecked Sep 20, 2026

Perplexity Sonar and Real-Time Agentic Search Pipeline

Aravind Srinivas · Perplexity AI

Architected Perplexity's conversational search engine and Sonar API, synthesizing real-time multi-source web crawling, dense vector retrieval, dynamic citation parsing, and fine-tuned LLM response generation with strict anti-hallucination attribution.

Scope & limitations

Subject to latency variance across heterogeneous external web APIs; adversarial or SEO-manipulated web sources require continuous algorithmic filtering.

Context: Llama-3-Sonar fine-tuned checkpoints, TensorRT-LLM, sub-second latency SLA, dynamic search grounding over live web indexes.

View mission
implementationChecked Sep 20, 2026

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Stella Biderman · EleutherAI / Booz Allen Hamilton

Directed the development and release of the Pythia model suite: 16 LLMs ranging from 70M to 12B parameters, all trained on identical data ordering with 154 intermediate checkpoints public for scientific analysis of memorization and bias.

Scope & limitations

Pre-training dataset contained early web corpora reflecting historical internet text distributions prior to modern RLHF curation.

Context: GPT-NeoX distributed training framework, FlashAttention, 300B tokens of the Pile dataset.

View mission
implementationChecked Sep 20, 2026

Real-Time Computer Vision Quality Control Pipeline for Manufacturing

Rahul Patel · Space-O Technologies / ManageMyClaw

Deployed an edge computer vision defect detection model running on industrial cameras that inspects automotive components on conveyor belts at 60 FPS with 99.4% precision.

Scope & limitations

Drastic variations in factory floor lighting conditions require automated photometric normalization algorithms.

Context: YOLOv8 on NVIDIA Jetson Orin Nano, TensorRT export, RTSP video streams.

View mission
Showing 145–160 of 241 proofs of work