inclusionAI / RingLinks
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
☆107Updated 4 months ago
Alternatives and similar repositories for Ring
Users that are interested in Ring are comparing it to the libraries listed below
Sorting:
- ☆87Updated 4 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆118Updated 7 months ago
- ☆85Updated 8 months ago
- ☆108Updated 3 months ago
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆80Updated this week
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆138Updated last year
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆187Updated 5 months ago
- The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]☆94Updated 8 months ago
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆144Updated 3 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 5 months ago
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆43Updated 10 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆131Updated 2 months ago
- A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward model…☆60Updated 6 months ago
- WideSearch: Benchmarking Agentic Broad Info-Seeking☆109Updated 2 months ago
- MrlX: A Multi-Agent Reinforcement Learning Framework☆157Updated last month
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆210Updated last month
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆282Updated last month
- ☆105Updated 2 weeks ago
- ☆126Updated 6 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆246Updated 4 months ago
- Efficient Agent Training for Computer Use☆134Updated 3 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆67Updated 8 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆112Updated 11 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆189Updated 9 months ago
- ☆105Updated last year
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆40Updated 4 months ago
- Scaling Preference Data Curation via Human-AI Synergy☆133Updated 5 months ago
- Towards a Unified View of Large Language Model Post-Training☆197Updated 3 months ago
- ☆93Updated 7 months ago
- ☆74Updated 6 months ago