ColinLu50 / SafeDeltaLinks
The official code repo for "Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets" in ICML 2025.
☆57Updated 6 months ago
Alternatives and similar repositories for SafeDelta
Users that are interested in SafeDelta are comparing it to the libraries listed below
Sorting:
- [NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs☆73Updated 2 months ago
- [ACL 25 main] Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model☆42Updated 2 months ago
- ☆164Updated 2 months ago
- [ACM MM 2025] Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation☆65Updated last week
- ☆84Updated 7 months ago
- [EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Ge…☆41Updated 11 months ago
- Repository of "Modal-NexT: toward unified heterogeneous cellular data integration"☆86Updated 7 months ago
- ☆63Updated 4 months ago
- Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward☆42Updated 2 months ago
- Code for ICCV 2025 paper - Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-T…☆107Updated 2 months ago
- A collection of papers related to knowledge fusion☆58Updated last year
- Official Code of Logits-Based-Finetuning☆91Updated 7 months ago
- [NeurIPS 2025] DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding☆74Updated 4 months ago
- ☆115Updated 6 months ago
- ☆134Updated 11 months ago
- HACAN: Hybrid Attention-Driven Cross-Layer Alignment Network for Image-Text Retrieval☆79Updated 8 months ago
- toolkit for WakenLLM framework☆47Updated 3 weeks ago
- Typeless Programming Language `sicpy` and Compiler;☆32Updated 2 years ago
- AutoRLAIF is a cutting-edge framework designed to revolutionize the fine-tuning of large language models through Reinforcement Learning …☆95Updated last year
- [ICLR 2025] Official implementation of paper "Improving Data Efficiency via Curating LLM-Driven Rating Systems"☆100Updated 9 months ago
- ☆62Updated last year
- ☆117Updated 4 months ago
- ☆116Updated 5 months ago
- ☆51Updated 8 months ago
- ☆73Updated 5 months ago
- ☆156Updated 2 months ago
- A high-performance Swift wrapper for MaxMind's GeoIP2 databases, offering thread-safe IP geolocation lookups with optimized memory manage…☆101Updated 8 months ago
- ☆121Updated last year
- Quick start with just one Python file for writing large models. No complex file structure or unnecessary explanations, perfect for beginn…☆41Updated 5 months ago
- This is a Spring Cloud project that integrates with AI Front-end vue3 Backend Spring Cloud Main function: It primarily achieves emotional…☆41Updated last week