This repository provides the implementation for studying Sycophancy-Induced Emerging Misalignment (EM) and introduces Gated Finetuning, a mechanism that enables training-free and instant reversal of EM through an inverted gated attention module.
☆17Oct 27, 2026Updated last week
Alternatives and similar repositories for Sycophancy_Emergent_Misalignment_and_Gated_attention_FT
Users that are interested in Sycophancy_Emergent_Misalignment_and_Gated_attention_FT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An AI-powered geopolitical intelligence platform that translates global events into real-time supply chain risk assessments, powered by G…☆26Oct 25, 2026Updated last week
- ☆38May 18, 2026Updated 5 months ago
- A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), …☆41Oct 28, 2026Updated last week
- [ECCV 2026] Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging☆37Mar 30, 2026Updated 7 months ago
- Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B mod…☆186Oct 7, 2026Updated 3 weeks ago
- 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.
- RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.☆56Updated this week
- A minimal, opinionated protocol for initializing new projects with both human-readable and agent-oriented documentation.☆38Oct 9, 2026Updated 3 weeks ago
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆20Dec 31, 2025Updated 10 months ago
- Know when your AI is about to forget — browser extension that monitors context window usage☆46Updated this week
- A curated list of papers on reinforcement learning post-training for LLMs☆52Sep 13, 2026Updated last month
- ☆21Jun 4, 2026Updated 5 months ago
- Open-source starter stack for Agent product developers: desktop client, control plane, workers, multi-agent workflows, admin, mobile, and…☆105Updated this week
- ☆30Jan 7, 2026Updated 9 months ago
- 🔥薄荷博客，基于.Net10后端+Vue3后台前端+Nuxt前台前端，实现的超漂亮博客系统。☆104Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆82Aug 19, 2026Updated 2 months ago
- 在 VSCode 中使用 Codex☆113Jul 5, 2026Updated 4 months ago
- EchoTest — Windows 桌面与安卓自动化测试工作台：操作录制与重放、原生 UI / 图像 / OCR 定位、低代码与 Python 用例、执行报告和 MCP 接入。☆49Updated this week
- Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan…☆41Updated this week
- AI competitor analysis backend powering analook.com. Generates competitor teardowns from any URL via FastAPI + Supabase.☆111Updated this week
- ☆321Jun 12, 2026Updated 4 months ago
- ☆31Jun 18, 2026Updated 4 months ago
- ☆27Jan 5, 2026Updated 10 months ago
- SafeHRC is an open-source codebase uniting HALO and SAGE to advance safe, adaptive, and generalizable human–robot collaboration.☆68Oct 24, 2026Updated last week
- 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.
- [ICCV'25] Radial Cross-Modal embeddings☆11Apr 27, 2026Updated 6 months ago
- Toolkit to benchmark the tamper-resistance of LLMs.☆36May 15, 2026Updated 5 months ago
- A reproducible ML study of Codeforces difficulty prediction, cold-start limits, temporal validation, and statement-structure features.☆33Sep 2, 2026Updated 2 months ago
- ☆106Aug 3, 2026Updated 3 months ago
- Paper list of LLM fingerprinting, based on our paper titled "SoK: Large Language Model Copyright Auditing via Fingerprinting".☆36Aug 28, 2025Updated last year
- ☆311Jun 17, 2026Updated 4 months ago
- USDT钱包靓号生成器,波场GPU靓号源码,TRON钱包靓号生成器☆80May 15, 2026Updated 5 months 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
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated 2 years 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.
- ☆53Oct 27, 2026Updated last week
- Code for Spectral Insights into Data-Oblivious Critical Layers in Large Language Models.☆11Jun 17, 2025Updated last year
- [NeurIPS 2025] I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions☆110Dec 30, 2025Updated 10 months 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
- 游戏策划作品展示：《恐怖小镇》方案与 Unity 原型实现记录☆48Oct 8, 2026Updated 3 weeks ago
- The official implementation of "Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment".☆10Mar 19, 2024Updated 2 years ago
- Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models☆11Mar 9, 2026Updated 7 months ago