Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"
☆11Feb 13, 2026Updated 8 months ago
Alternatives and similar repositories for model-diffing
Users that are interested in model-diffing are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features (ICML 2026)☆12May 18, 2026Updated 5 months ago
- ☆13Sep 9, 2016Updated 10 years ago
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆34Oct 5, 2026Updated 3 weeks ago
- ☆11Jun 17, 2024Updated 2 years ago
- An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks [ICML 2025]☆12Jun 11, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Prometheus exporter for aiohttp client and server.☆16Mar 6, 2023Updated 3 years ago
- Slides and demo code for my presentation entitled Beyond the Basics with Azure ML.☆12Sep 7, 2026Updated last month
- home to all the generative art code I create for YouTube and IG tutorials☆35Apr 30, 2022Updated 4 years ago
- Adopt-A-CivicArt project collaboration with the County Arts Commission☆10May 1, 2019Updated 7 years ago
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 6 months ago
- [CVPR2026 Highlight] Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucinat…☆21Aug 9, 2026Updated 2 months ago
- Python package and CLI tool for social choice functions☆14Jun 20, 2021Updated 5 years ago
- What are the best Systems? New Perspectives on NLP Benchmarking☆13Mar 16, 2023Updated 3 years ago
- PyPiano is a python library to programmatically play piano. It is an easy to use abstraction layer on top of the python-mingus package pr…☆20Oct 6, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for the AAAI-2021 paper: C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling☆16Mar 9, 2021Updated 5 years ago
- ☆13Sep 13, 2023Updated 3 years ago
- Smart Document API turns PDFs, Office documents, and images into structured layouts, OCR text, tables, formulas, and Markdown for AI-powe…☆26Jul 14, 2026Updated 3 months ago
- ☆18Nov 30, 2022Updated 3 years ago
- ☆11Feb 25, 2024Updated 2 years ago
- Paranoid Transformer for NaNoGenMo☆19Nov 1, 2020Updated 5 years ago
- Water Hackweek Machine Learning workshop☆15Sep 2, 2020Updated 6 years ago
- We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true …☆14May 13, 2024Updated 2 years ago
- Open source library for few shot NLP☆78Jun 25, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆15Aug 10, 2026Updated 2 months ago
- Digital Design Lab Spring 2019 Final Project☆13Jun 17, 2019Updated 7 years ago
- ☆29Jun 5, 2026Updated 4 months ago
- Collective effort to solve matan☆10Mar 17, 2021Updated 5 years ago
- ☆11Dec 17, 2021Updated 4 years ago
- A Common Lisp client for freesound.org☆10Mar 18, 2021Updated 5 years ago
- ☆21Jan 5, 2022Updated 4 years ago
- A python tool to study scalar field dynamics in cosmology☆11Apr 24, 2023Updated 3 years ago
- Chatbot that draws charts. Dialogflow, python, pygal☆10Sep 13, 2018Updated 8 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Experimental support for importing Kotlin code into Java projects via a JDT.LS extension☆27Jul 29, 2024Updated 2 years ago
- Backtrace.io's resilient log record framing format☆42Feb 5, 2022Updated 4 years ago
- Paper Implementation of Self-Rewarding Language Models☆13Feb 1, 2024Updated 2 years ago
- install `dotenvx` via curl☆12Oct 20, 2026Updated last week
- The AI engineer roadmap for agent builders: a staged path with runnable labs to build a coding agent from scratch - by AI Builder Club☆28Jul 6, 2026Updated 3 months ago
- Communication-Cost Aware Microphone Selection For Neural Speech Enhancement with Ad-hoc Microphone Arrays☆17Nov 20, 2020Updated 5 years ago
- End-to-end Snowplow Analytics Pipeline for real time events☆29Jul 18, 2023Updated 3 years ago