---
title: README
emoji: 🚀
colorFrom: green
colorTo: pink
sdk: docker
pinned: true
license: apache-2.0
short_description: Building safe and resilient partners in thought.
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/686c460ba3fc457ad14ab6f8/ffK_ttxC_5boGIKNMVOZc.png
---

<div align="center">

![vanta_trimmed](https://cdn-uploads.huggingface.co/production/uploads/686c460ba3fc457ad14ab6f8/hcGtMtCIizEZG_OuCvfac.png)
  
  <h1>VANTA Research</h1>
    
  <p><strong>Independent AI research lab building safe, resilient language models optimized for human-AI collaboration</strong></p>
  
  <p>
    <a href="https://vantaresearch.xyz"><img src="https://img.shields.io/badge/Website-vantaresearch.xyz-black" alt="Website"/></a>
    <a href="https://x.com/vanta_research"><img src="https://img.shields.io/badge/@vanta_research-1DA1F2?logo=x" alt="X"/></a>
    <a href="https://github.com/vanta-research"><img src="https://img.shields.io/badge/GitHub-vanta--research-181717?logo=github" alt="GitHub"/></a>
  </p>
</div>

---

## Mission

VANTA Research develops language models highly optimized for human-AI collaboration. Additionally, VANTA Research produces work in:
1. **Pushing beyond standard benchmarks** - Surface capabilities invisible to traditional evaluation
2. **Exposing where models collapse, deceive, or diverge** - Systematic stress-testing for safety
3. **Developing innovative tooling to advance AI research** - Open-source frameworks for the community

We believe AI safety research should be accessible, transparent, and built for cognitive diversity.

---

## Featured Models

### [**Atom-Olmo3-7B**](https://huggingface.co/vanta-research/atom-olmo3-7b)
Specialized language model fine-tuned for collaborative problem-solving and creative exploration. Built on the Olmo-3-7B-Instruct foundation, this model brings thoughtful, structured analysis to complex questions while maintaining an engaging, conversational tone.

### [**Mox-Tiny-1**](https://huggingface.co/vanta-research/mox-tiny-1)
Unlike traditional assistants that optimize for user satisfaction through validation, Mox will: - Give you direct opinions instead of endless hedging - Push back when your premise is flawed - Admit uncertainty rather than fake confidence - Engage with genuine curiosity and occasional humor.

*Looking for quantizations of our models? We try to include 4 bit quants in each model repo, but if you are looking for more quantization types, we recommend [team mradermacher](https://huggingface.co/mradermacher) who regularly provide high quality quantizations of our models in various sizes/formats. Thank you, team mradermacher.*

---

## Research Contributions

### **VRRE (VANTA Research Reasoning Evaluation)**
Novel semantic-based benchmark that detected a **2.5x reasoning improvement** completely invisible to standard benchmarks. This suggests we're systematically missing capability improvements when we "teach to the test."

[Read the paper →](https://zenodo.org/records/17162683)

### **Persona Collapse Framework**
Systematic characterization of reproducible failure modes in LLMs under atypical cognitive stress. Identifies alignment blind spots invisible to standard evaluations.

[Read the paper →](https://zenodo.org/records/17188172)

### **Cognitive Fit vs. Alignment**
Argument for personalized synchronization in AI systems rather than universal "alignment" - recognizing that optimal model behavior depends on user's cognitive style.

[Read the paper →](https://zenodo.org/records/17346467)

---


## Open Source Philosophy

We stand on the shoulders of the open-source contributors who came before us. Our commitment is to contribute back and make AI development more accessible, transparent, and beneficial for all.

---

## Connect

**Interested in sponsoring our open source work?**

We are actively seeking partnerships/sponserships for API access/compute/funding. 

VANTA Research is completely independent and self-funded. If you'd like to fuel our contributions to open source AI, please reach out using one of the methods below:

- **Email:** hello@vantaresearch.xyz
- **Website:** [vantaresearch.xyz](https://vantaresearch.xyz)
- **Twitter/X:** [@vanta_research](https://x.com/vanta_research)
- **GitHub:** [vanta-research](https://github.com/vanta-research)
- **Support:** [VANTA Research Merch Store](https://merch.vantaresearch.xyz) - *100% of proceeds from the online store are reinvested back into VANTA Research's open source contributions (compute, hardware, APIs, storage, etc).*


---