Official code repository for the paper "Internal Activation as the Polar Star for Steering Unsafe LLM Behavior"
☆16May 31, 2026Updated 5 months ago
Alternatives and similar repositories for SafeSwitch
Users that are interested in SafeSwitch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official code repository for the paper "ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind"☆27Sep 25, 2025Updated last year
- Official repo for "Binary Retrieval-augmented Reward Mitigates Hallucinations"☆16Nov 13, 2025Updated last year
- ☆21Apr 21, 2026Updated 6 months ago
- ☆13Jun 19, 2025Updated last year
- Code for paper: "LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits"☆14Sep 19, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [WWW 2026 Oral] MoE-CL:Self-Evolving LLMs via Continual Instruction Tuning☆22Dec 1, 2025Updated 11 months ago
- Discover, evaluate, and intervene on circuits in transformer models.☆32Updated this week
- Lightweight, composable framework for building muti-agent systems with Model Context Protocol (MCP)☆15Mar 23, 2025Updated last year
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- ☆10Sep 9, 2024Updated 2 years ago
- [ACL 2026] Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment☆14May 11, 2026Updated 6 months ago
- ☆24Nov 5, 2024Updated 2 years ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- Source code of AsiaCCS'22 paper - RecIPE: Revisiting the Evaluation of Memory Error Defenses☆14Sep 19, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples☆11Oct 14, 2024Updated 2 years ago
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- UI-CTX: demystifying Android UI behaviors with a concise and effective representation, in NDSS '25☆14Jan 17, 2025Updated last year
- [EMNLP 2025 Outstanding Paper Award] Official repo for DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph …☆22Nov 16, 2025Updated last year
- [CVPR 2023] "TrojViT: Trojan Insertion in Vision Transformers" by Mengxin Zheng, Qian Lou, Lei Jiang☆15Jan 5, 2024Updated 2 years ago
- ☆50Oct 1, 2024Updated 2 years ago
- Official PyTorch implementation for Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability [Neur…☆17Jul 7, 2025Updated last year
- Offical repository for NeurIPS 2025 paper "From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monito…☆14May 5, 2026Updated 6 months ago
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆16Jun 18, 2025Updated last year
- ☆16Dec 11, 2025Updated 11 months ago
- The reinforcement learning codes for dataset SPA-VL☆48Jun 24, 2024Updated 2 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Jan 3, 2023Updated 3 years ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- Overflow Prevention Enhances Long-Context Recurrent LLMs (COLM 2025)☆19Jul 8, 2025Updated last year
- [ACL 2026] Rethinking Expert Trajectory Utilization in LLM Post-training☆13Jun 30, 2026Updated 4 months ago
- Official implementation of 'RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training', accepted by ICLR 2026☆19Oct 15, 2025Updated last year
- ☆18Oct 7, 2022Updated 4 years 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.
- ☆12Apr 6, 2026Updated 7 months ago
- Repository for the paper: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning☆19Feb 21, 2025Updated last year
- 智能医疗问诊系统 - LangGraph Agent + RAG + React☆25Jan 27, 2026Updated 9 months ago
- ☆18May 15, 2026Updated 6 months ago
- A simple implementation of ReasonGenRM.☆19Apr 21, 2025Updated last year
- Adversarial examples to the new ConvNeXt architecture☆20Jan 12, 2022Updated 4 years ago
- ☆50Dec 9, 2025Updated 11 months ago
Are these results useful?