ML scientist exploring how LLMs navigate multi-agent scenarios through projects like NegotiationArena, bridging Stanford NLP research with open source tooling.
TextGrad. I built a system that improves AI models through written feedback.
3.7kOpen Data Scientist. I built an AI assistant that analyzes datasets and generates reports automatically.
187FashionCLIP. I built an AI model that connects fashion photos to written descriptions.
530Einstein Arena. I built a platform where AI agents compete on unsolved math problems.
40PLIP. I built an AI model that reads pathology images and medical text together.
382NegotiationArena. I built a platform that tests how well AI models can negotiate with each other.
84Safety-Tuned LLaMAs. I built datasets and code studying how to safely tune instruction-following AI models.
95RecList. I made a testing toolkit for recommendation systems that catches real problems.
475Vision Language Tuner. I researched why image-text models ignore word order and found solutions.
294Data. I collected datasets in one place so builders can start working faster.
2PathClip. I built a tool that finds matching images using artificial intelligence.
2Compass. I built a tool that makes word meanings consistent across different text sources.
43Track Meaning. I built a tool to show what AI models focus on when reading text.
1Design Good Figures. I made a tool that turns research data into presentation-ready visuals.
4Aligned Word Embeddings. I built a tool that aligns AI word meanings across different datasets.
1Entity2Vec. I made a tool that learns entity relationships through type embeddings.
1Cosine Search. I built a plugin that finds similar documents in Elasticsearch.
3AI Distillery. I built a tool that summarizes the constant flood of AI research papers.
25Logic Tensor Networks. I made experiments showing how machines learn logical relationships from data.
6Speech Nuance. I made a dataset showing harmful speech has many different shapes.
2Tweet Topics. I built a tool that finds hidden topics in tweets across different days.
1Research Transformers. I built tools for training and using AI models in Python.
1Bias Check. I built a tool that measures demographic stereotypes in AI image generators.
5Twitter Research Kit. I built scripts that collect and store Twitter data for research.
61PassEl. I built a tool that pulls passwords from 1Password into Emacs.
5Omnivector. I made a tool that normalizes data from many different sources.
1Reasoner. I built a tool that traces logical chains through connected information.
2Prod. I built a shared workspace where teams track and showcase their work.
1Prodb. I made a tool that helps you search through Python code.
18Logical Commonsense. I built a tool that helps AI understand common sense reasoning.
1Fashion Search. I built a fashion image search engine you can deploy yourself.
3Paca. I made a tool that grades how well AI models answer questions.
1Chronos. I documented research on how word meanings shift over time.
1Time-Aware. I built AI models that understand how meaning changes over time.
1Social Diffusers. I built a way for groups to share one AI image generator.
1Clip Tuner. I built a tool to customize how AI models recognize images.
2BertLang. I made a searchable guide to language-specific AI text models.
18Quica. I built a tool that measures when multiple people agree on labeling data.
23MiniSearch. I built a search tool that answers questions about research papers.
2