[NeurIPS 2025] Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation.
☆14Jul 28, 2026Updated 2 months ago
Alternatives and similar repositories for Panacea
Users that are interested in Panacea are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 9 months ago
- DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation.☆143Feb 10, 2026Updated 8 months ago
- [EMNLP Main 2026]VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning.☆26Jul 20, 2026Updated 3 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆43Mar 22, 2025Updated last year
- ☆12Jul 10, 2023Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- MLLM, DeepResearch, Agentic AI☆24Jun 1, 2026Updated 4 months ago
- ☆20Jun 21, 2025Updated last year
- ☆63Jun 7, 2025Updated last year
- ☆24Dec 8, 2024Updated last year
- [NeurIPS 2025] Reasoning MLLM, Share-GRPO, advantage vanishing, sparse reward☆37Sep 19, 2025Updated last year
- Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Reinforcement Learning☆35May 11, 2026Updated 5 months ago
- OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents☆15May 27, 2026Updated 4 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆100Feb 21, 2025Updated last year
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆30Oct 23, 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.
- [ICCV 2025] MMReason, MLLMs, step by step, reasoning benchmark, AGI☆15Apr 25, 2026Updated 6 months ago
- ☆29May 14, 2025Updated last year
- 🧭 SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages☆13Feb 12, 2025Updated last year
- ☆37Oct 10, 2024Updated 2 years ago
- NeurIPS'24 - LLM Safety Landscape☆41Oct 21, 2025Updated last year
- ☆50Sep 29, 2024Updated 2 years ago
- ☆12Feb 19, 2024Updated 2 years ago
- ☆39Jan 13, 2022Updated 4 years ago
- SWE Arena☆37Jul 6, 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.
- This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"☆56Feb 2, 2025Updated last year
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆38Jul 10, 2025Updated last year
- Codes for replicating the dataset described in "A Satellite Imagery Dataset for Long-Term Sustainable Development in United States Cities…☆12Jun 23, 2023Updated 3 years ago
- The implementation of Meta-Pec☆14Sep 13, 2023Updated 3 years ago
- Inference-time alignment for harmlessness through cross-model guidance (ACL 2024). Code + MM-Harmful Bench.☆38Oct 2, 2024Updated 2 years ago
- A survey on harmful fine-tuning attack for large language model (ACM CSUR)☆251Sep 6, 2026Updated last month
- The loss landscape of Large Language Models resemble basin!☆49Jul 8, 2025Updated last year
- Repository containing the website for the EMNLP 2023 conference☆17Feb 12, 2025Updated last year
- Demo code for the paper: One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features☆12Nov 30, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated 2 years ago
- 基于 Go 的 HTTP 中继工具，为你的服务器请求 OpenAI 的 API 提供 中继服务，也可用于搭建镜像站，开箱即用. Golang based HTTP relay server.☆12Apr 19, 2023Updated 3 years ago
- [AAAI26] Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitie…☆11Feb 7, 2026Updated 8 months ago
- [NeurIPS 2025 D&B Track] Benchmarking Language Models on Imperfect Tabular Data☆13Jul 31, 2025Updated last year
- Your finetuned model's back to its original safety standards faster than you can say "SafetyLock"!☆11Oct 16, 2024Updated 2 years ago
- ☆13Apr 27, 2024Updated 2 years ago
- [NeurIPS'24] "NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes" by Hao-Lun …☆10Sep 18, 2025Updated last year