https://scale.com/research/mrt
☆21Mar 16, 2026Updated 8 months ago
Alternatives and similar repositories for mrt
Users that are interested in mrt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆65Jul 29, 2026Updated 3 months ago
- Research into chain-of-thought monitoring as an AI Control protocol☆14Jun 29, 2025Updated last year
- [ICLR 2026] Monitoring Decomposition Attacks with Lightweight Sequential Monitors☆12Apr 20, 2026Updated 6 months ago
- Codebase for Distillation Robustifies Unlearning☆11Jun 11, 2025Updated last year
- [ICML 2025] Official implementation for "The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for L…☆15May 23, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆26Oct 22, 2026Updated 3 weeks ago
- Official repo for SteeringSafety☆11Oct 16, 2025Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆14Jun 20, 2025Updated last year
- Code used for "Training Agents to Self-Report Misbehavior"☆21Feb 27, 2026Updated 8 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Jul 9, 2024Updated 2 years ago
- ☆29Sep 3, 2025Updated last year
- Open-sourced evaluation suite from the Monitoring Monitorability paper☆110Aug 17, 2026Updated 3 months ago
- ☆29Aug 31, 2025Updated last year
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆41Sep 17, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆29Oct 6, 2024Updated 2 years ago
- [ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability☆61Mar 10, 2026Updated 8 months ago
- ☆201Oct 31, 2025Updated last year
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Oct 6, 2026Updated last month
- Official implementation for "DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling" (IEEE S&P 2026)☆14Jan 28, 2026Updated 9 months ago
- ☆10Jan 28, 2019Updated 7 years ago
- Build and train systems of agents.☆35Nov 12, 2026Updated last week
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆194Apr 23, 2025Updated last year
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆10Oct 7, 2026Updated last month
- [ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents☆29Feb 17, 2026Updated 9 months ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆67Feb 9, 2026Updated 9 months ago
- [NeurIPS 2025]: Personalized Safety in LLMs — A Benchmark and a Planning-Based Agent Approach☆18Oct 30, 2025Updated last year
- An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human in…☆32May 24, 2026Updated 5 months ago
- [CCS 2026] The official implementation of our CCS 2026 paper "ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathological…☆19Aug 5, 2026Updated 3 months ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆270Updated this week
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆21Mar 31, 2025Updated last year
- ☆14Feb 12, 2026Updated 9 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Generate realistic and diverse user personas for LLM agent benchmarks.☆13Oct 18, 2026Updated last month
- ☆24Mar 18, 2025Updated last year
- Code for ACL 2025 accepted paper titled "MPO: Multilingual Safety Alignment via Reward Gap Optimization"☆12Jun 5, 2025Updated last year
- A further improvement for the AutoDAN-Turbo through test-time scaling.☆16Oct 21, 2025Updated last year
- [ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron☆36Apr 30, 2025Updated last year
- Conjure home-grown, auto-expanding context from Logseq into agent conversations.☆17Jul 17, 2026Updated 4 months ago
- Code for the paper "Emergent Collusion in Long-Horizon LLM Agent Interaction"☆20Sep 24, 2026Updated last month
Are these results useful?