lasgroup / SafetyPolytopeLinks
Learning Safety Constraints for Large Language Models (ICML2025)
☆23Updated 2 months ago
Alternatives and similar repositories for SafetyPolytope
Users that are interested in SafetyPolytope are comparing it to the libraries listed below
Sorting:
- ☆34Updated 2 years ago
- Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"☆32Updated last year
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- Attack AlphaZero Go agents (NeurIPS 2022)☆22Updated 2 years ago
- Rewarded soups official implementation☆60Updated 2 years ago
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆42Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated last year
- Representation Learning in RL☆13Updated 3 years ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆19Updated 11 months ago
- ☆18Updated last year
- ☆18Updated 11 months ago
- ☆11Updated 10 months ago
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆37Updated last year
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆38Updated last year
- ☆13Updated last year
- [NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning☆34Updated 4 years ago
- ☆19Updated 11 months ago
- ☆10Updated 3 years ago
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆59Updated last year
- [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective☆38Updated last month
- Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (M…☆29Updated 11 months ago
- [AutoML'22] Bayesian Generational Population-based Training (BG-PBT)☆29Updated 3 years ago
- Provably (and non-vacuously) bounding test error of deep neural networks under distribution shift with unlabeled test data.