Learning Safety Constraints for Large Language Models (ICML2025)
☆35May 25, 2026Updated 2 months ago
Alternatives and similar repositories for SafetyPolytope
Users that are interested in SafetyPolytope are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆17Jun 2, 2025Updated last year
- Robust and safe deep reinforcement learning algorithms☆17Mar 27, 2024Updated 2 years ago
- Scaling safe exploration to vision control☆15Feb 19, 2025Updated last year
- The implementation of our IEEE S&P 2024 paper "Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples".☆11Jun 28, 2024Updated 2 years ago
- MISO: Learning Multiple Initial Solutions to Optimization Problems☆18Jun 18, 2026Updated last month
- 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.
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆30Jan 29, 2026Updated 6 months ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆15Jan 13, 2023Updated 3 years ago
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆18Jun 24, 2026Updated last month
- ☆14Mar 30, 2025Updated last year
- A package for realtime wheeled robot motion planning and collision-free control☆19Aug 27, 2020Updated 5 years ago
- A collection of algorithms and experiment tools for safe sim to real transfer in robotics.☆28May 19, 2026Updated 2 months ago
- ☆15Jun 30, 2025Updated last year
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆35Jan 31, 2025Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆34Sep 18, 2025Updated 10 months 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.
- A fast and light G-INS-Odometry system.☆18Apr 10, 2026Updated 4 months ago
- ☆33Jul 4, 2024Updated 2 years ago
- [NDSS'25] The official implementation of safety misalignment.☆19Jan 8, 2025Updated last year
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆59Jul 24, 2026Updated 2 weeks ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 2 months ago
- ☆33Jun 24, 2024Updated 2 years ago
- Common functionality for object detection☆16May 4, 2021Updated 5 years ago
- Implementing DQNClipped and DQNReg Algorithms☆10Mar 2, 2021Updated 5 years ago
- [ACL'24 Findings] Official code for "TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback"☆12Dec 6, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [IROS2024] STAIR: Semantic-Targeted Active Implicit Reconstruction☆16Aug 3, 2024Updated 2 years ago
- [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning☆32Dec 2, 2023Updated 2 years ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆57Sep 19, 2023Updated 2 years ago
- ☆14Sep 29, 2025Updated 10 months ago
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 4 years ago
- Flow RL is a high-performance RL library with flow and diffusion models.☆44Jul 27, 2026Updated 2 weeks ago
- The code implementation of MuScleLoRA (Accepted in ACL 2024)☆10Dec 1, 2024Updated last year
- Train text generation model with JavaScript.☆15Jul 14, 2024Updated 2 years ago
- Deploy RL on your Real-World Franka Emika Panda☆14Feb 22, 2026Updated 5 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.
- Convergent Policy Optimization for Safe Reinforcement Learning☆11Oct 26, 2019Updated 6 years ago
- This is a repository of DQN and its variants implementation in PyTorch based on the original papar.☆13Nov 18, 2019Updated 6 years ago
- ☆18May 14, 2026Updated 2 months ago
- A benchmark for evaluating reinforcement learning algorithms that train the policies using imaginary rollouts from LLMs.☆15Nov 4, 2025Updated 9 months ago
- Official repository for "On the Multi-modal Vulnerability of Diffusion Models"☆17Jul 15, 2024Updated 2 years ago
- ☆24Mar 6, 2025Updated last year
- Backdooring Neural Code Search☆14Sep 8, 2023Updated 2 years ago