AlignmentResearch / learned-plannerLinks
Interpreting Learned Search and Planning: Reverse-engineering recurrent convolutional networks (DRC) that play Sokoban
☆15Updated 5 months ago
Alternatives and similar repositories for learned-planner
Users that are interested in learned-planner are comparing it to the libraries listed below
Sorting:
- Measuring the situational awareness of language models☆39Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆65Updated 9 months ago
- Minimum Description Length probing for neural network representations☆20Updated 10 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated 2 years ago
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 9 months ago
- REBUS: A Robust Evaluation Benchmark of Understanding Symbols☆13Updated last year
- Clean RL implementation using MLX☆33Updated last year
- A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks☆36Updated last year
- ☆30Updated 2 years ago
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆29Updated this week
- ☆62Updated 5 months ago
- ☆55Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated last year
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated last year
- Code repo for MathAgent☆17Updated last year
- [ICLR 2025] Code for the paper "Implicit Search via Discrete Diffusion: A Study on Chess"☆36Updated 8 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆112Updated last month
- ⚓️ Interactive playground for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆17Updated 3 months ago
- Scripts for downloading and pre-processing the `proof-pile`, a high quality dataset of mathematical text and code.☆21Updated 3 years ago
- CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)☆72Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆70Updated 2 years ago
- Simple repository for training small reasoning models☆46Updated 9 months ago
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆41Updated last year
- Evaluating LLMs with CommonGen-Lite☆91Updated last year
- UQ: Assessing Language Models on Unsolved Questions☆28Updated 3 months ago
- ☆80Updated 8 months ago
- ☆59Updated 3 weeks ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated last year
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆94Updated 6 months ago
- Generating and validating natural-language explanations for the brain.☆59Updated 2 weeks ago