Subliminal learning in LLMs: language models can transmit hidden preferences through seemingly unrelated training data.
☆26Nov 9, 2025Updated last year
Alternatives and similar repositories for owls
Users that are interested in owls are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆165Feb 10, 2026Updated 9 months ago
- Codebase for the paper "A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language"☆11Oct 11, 2024Updated 2 years ago
- ☆17Sep 11, 2026Updated 2 months ago
- ☆20Jun 3, 2026Updated 5 months ago
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Nov 3, 2026Updated 2 weeks 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.
- ☆34Sep 3, 2026Updated 2 months ago
- Mapping out the "memory" of neural nets with data attribution☆113Updated this week
- ☆31May 4, 2023Updated 3 years ago
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated last year
- Code for "Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models".☆23Mar 16, 2026Updated 8 months ago
- ☆16Jun 18, 2025Updated last year
- Code and materials for "Weird Generalization and Inductive Backdoors"☆43Jan 11, 2026Updated 10 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆19Mar 15, 2024Updated 2 years ago
- An MLX implementation of Meta AI's ESM-2 protein language model☆16Aug 16, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [EMNLP 2025 Oral] 🎉 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs☆15Dec 10, 2025Updated 11 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆90Oct 25, 2026Updated 3 weeks ago
- ☆21Updated this week
- Source code for Activated LoRA☆27Oct 30, 2026Updated 2 weeks ago
- Official code release for Delta Activations: A Representation for Finetuned Large Language Models☆22Sep 5, 2025Updated last year
- Repository for the paper: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning☆19Feb 21, 2025Updated last year
- Machine Learning for Alignment Bootcamp☆28Mar 7, 2024Updated 2 years ago
- Implementation for Proximal Neural Networks.☆11Sep 17, 2021Updated 5 years ago
- Multi-Word Probabilistic based supertokenizer☆15May 15, 2025Updated last year
- 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.
- Official implementation of the paper "Agentic Backdoors via Pretraining Poisoning"☆18Updated this week
- Exploring Model Kinship for Merging Large Language Models☆28Apr 16, 2025Updated last year
- ☆23Aug 25, 2026Updated 2 months ago
- Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL" (arxiv.org/abs/2602.04417)☆11Feb 5, 2026Updated 9 months ago
- How Well Does Agent Development Reflect Real-World Work?☆17Feb 26, 2026Updated 8 months ago
- Landing repository for the paper "Predicting the Order of Upcoming Tokens Improves Language Modeling"☆48May 13, 2026Updated 6 months ago
- ☆18Sep 11, 2026Updated 2 months ago
- ☆31Jan 7, 2026Updated 10 months ago
- Pixels, Patterns, but no Poetry: To See the World like Humans☆18Aug 11, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆13Oct 15, 2023Updated 3 years ago
- 🙌 Take your React skills beyond average☆10Sep 22, 2026Updated last month
- ☆24Jun 16, 2026Updated 5 months ago
- ☆28May 14, 2026Updated 6 months ago
- Training Coder Models with Critique Reinforcement Learning [ICLR26]☆13Apr 11, 2026Updated 7 months ago
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆22Sep 24, 2025Updated last year
- select videos and notes☆11Aug 6, 2026Updated 3 months ago
Are these results useful?