liziniu / cold_start_rlLinks
Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?
☆17Updated 4 months ago
Alternatives and similar repositories for cold_start_rl
Users that are interested in cold_start_rl are comparing it to the libraries listed below
Sorting:
- ☆19Updated 7 months ago
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆38Updated 5 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆33Updated last week
- Long Context Extension and Generalization in LLMs☆58Updated 10 months ago
- Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)☆25Updated 8 months ago
- Codebase for Instruction Following without Instruction Tuning☆35Updated 10 months ago
- ☆82Updated 6 months ago
- Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆41Updated last month
- [NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"☆38Updated last year
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆59Updated 5 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆28Updated 4 months ago
- ☆71Updated 4 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆105Updated 2 months ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆52Updated 5 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 9 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆92Updated last week
- A scalable automated alignment method for large language models. Resources for "Aligning Large Language Models via Self-Steering Optimiza…☆20Updated 8 months ago
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆101Updated 2 months ago
- The official repository of the Omni-MATH benchmark.☆85Updated 7 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 2 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆46Updated 2 months ago
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆102Updated 4 months ago
- Code for paper "Patch-Level Training for Large Language Models"☆86Updated 8 months ago
- ☆52Updated last month
- The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]☆87Updated 3 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆168Updated 3 weeks ago
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning☆52Updated last month
- [ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches☆52Updated 4 months ago
- ☆65Updated last year