[ACL 2026] - Official repo for the paper: "Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection"
☆12Sep 13, 2026Updated 2 months ago
Alternatives and similar repositories for steering
Users that are interested in steering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Nov 11, 2025Updated last year
- Codex Skill for AutoDL remote GPU experiments with email progress alerts☆11Apr 25, 2026Updated 6 months ago
- Resources Links for the Research Based on Josh Prager and Nico Shyne's☆13Oct 21, 2024Updated 2 years ago
- Supergoal is a Codex skill that turns ambitious engineering ideas into dependency-aware sub-goals, intelligently designs verification for…☆11Jun 24, 2026Updated 4 months ago
- FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving☆12Aug 3, 2026Updated 3 months ago
- 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.
- The code for the EACL 2023 paper "PromptDA: Label-guided Data Augmentation for Prompt-based Few-Shot Learners"☆10Oct 18, 2023Updated 3 years ago
- Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents☆12Feb 23, 2026Updated 8 months ago
- ☆13Oct 11, 2026Updated last month
- Vision Transformer Finetuning Benefits from Non-Smooth Components☆11Sep 10, 2026Updated 2 months ago
- 🏝️ Code for our paper: "Privasis: Synthesizing the Largest 'Public' Private Dataset from Scratch"☆16Jul 10, 2026Updated 4 months ago
- ☆10Apr 25, 2022Updated 4 years ago
- CREST is a training-free test-time steering framework that discovers cognitive heads via simple offline calibration and then rotates acti…☆12Oct 22, 2026Updated 3 weeks ago
- ☆16Jun 17, 2026Updated 4 months ago
- A Home Assistant frontend custom card for the ha-nfl integration.☆15Sep 5, 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.
- ☆13Feb 5, 2026Updated 9 months ago
- Code for "TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents (AAAI 2026 Oral)"☆14Aug 31, 2026Updated 2 months ago
- [ICML 2023] Code for "A Three-regime Model of Network Pruning"☆11Oct 20, 2023Updated 3 years ago
- A compact Codex skill for proportional coding, testing, ML validation, and academic writing.☆26Aug 14, 2026Updated 3 months ago
- UniDoc-RL: Unified Document Understanding with Reinforcement Learning☆18May 21, 2026Updated 5 months ago
- Code for ACL 2022 long paper: Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View☆10May 17, 2022Updated 4 years ago
- Build coherent and visually polished multimodal webpages with hierarchical planning, AIGC tools, and iterative reflection.☆18May 17, 2026Updated 5 months ago
- ☆15Jul 20, 2026Updated 3 months ago
- ☆12May 14, 2026Updated 6 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Teaching a humanoid to walk(ish), then displaying in your browser (using tensorflow.js and reinforcement learning)☆10Sep 7, 2020Updated 6 years ago
- Official implementation for the paper "Video-Based Reward Modeling for Computer-Use Agents"☆18Mar 14, 2026Updated 8 months ago
- Code for "MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training" at ICML 2026☆19May 13, 2026Updated 6 months ago
- Concise Reasoning via Reinforcement Learning☆13Apr 16, 2025Updated last year
- [KDD 2023] code for "Test accuracy vs. generalization gap: model selection in NLP without accessing training or testing data" https://arx…☆12Oct 17, 2022Updated 4 years ago
- [NeurIPS 2026 Pre-to-Post] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆20Apr 16, 2026Updated 6 months ago
- This framework implements key experiments on the sparse double descent phenomenon (ICML 2022).☆15Dec 13, 2022Updated 3 years ago
- ☆12Aug 27, 2024Updated 2 years ago
- ☆18Mar 10, 2026Updated 8 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- AI 驱动的学术论文深度分析工具：MinerU 解析 + Claude 生成图文技术文章 + GitHub 代码级创新点定位，结果自动存入 Obsidian vault☆24Mar 25, 2026Updated 7 months ago
- Finite time Lyapunov exponent (FTLE) from analytical velocity field☆11Jun 29, 2020Updated 6 years ago
- DeepControl: Neural Network Controller for Quadrotor☆10Jan 5, 2020Updated 6 years ago
- MWM: Mobile World Models for Action-Conditioned Consistent Prediction☆17Apr 10, 2026Updated 7 months ago
- [EMNLP 2024 Oral] Model Balancing Helps Low Data Training and Fine-tuning☆13Oct 22, 2025Updated last year
- PyTorch implementation of LAMB for ImageNet/ResNet-50 training☆13May 13, 2021Updated 5 years ago
- ☆20May 25, 2026Updated 5 months ago
Are these results useful?