Large-scale pretrained models for goal-directed dialog

Open-vocabulary Object Segmentation with Diffusion Models

This is a list of open-source projects at Microsoft Research NLP Group

Deterministic multi-LLM orchestration with grounded, verified answers, an editable guardrail gate, and a live process dashboard.

Beginner-friendly Python RAG project that turns StackOverflow Q&A data into a grounded knowledge assistant using sentence-transformer embeddings, FAISS retrieval, and strict citation-based LLM answering.

Developer-first prompt engineering patterns for grounded, testable, and reliable AI outputs.

ComfyUI Custom Nodes for Gen Searcher and other tools

Secure Enterprise RAG platform with RBAC enforcement, OWASP LLM defenses, hybrid retrieval, grounded generation, explainability, and zero-trust context pipelines.

Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.

Turn a product idea into a grounded, buildable SRD suite — a skills.sh agent skill

Adaptive quiz generation from PDFs using interpretable NLP, grounded LLMs, and deep knowledge tracing.

Multi-agent resume & cover-letter engine — grounded generation with a hard groundedness gate, ATS/recruiter simulation, dual-model QC.

Grounded RAG v1 specification with abstain/partial semantics

URIM is a local grounded chat runtime for querying boxed authority content with a fixed, deterministic retrieval pipeline.

RAG system for Trine University international students. Provides grounded answers on admissions, CPT/OPT, scholarships, insurance using 10 FAQ documents. Built with Python, ChromaDB, Groq LLM, and Gradio UI

Personal RAG avatar agent that answers in my voice using a private, continuously evolving knowledge base with grounded retrieval.

Strictly-grounded RAG chat on Adobe Spectrum docs — Algolia Agent Studio + Algolia index. Per-answer grounding judge (3-judge panel: Skeptic/Referee/Advocate) surfaced as a Confidence chip → breakdown drawer. Reusable Algolia-Central-[company] template.

KG-based Text World Models & Semantic Dynamics for Conversational AI — build, simulate, and reason over a user's semantic world with text-native graphs and time-aware rules.

Query an Obsidian or Markdown vault with local retrieval, exact selected-source citation validation and fail-closed refusal.