stepfun-ai / PaCoReLinks
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
☆292Updated 2 weeks ago
Alternatives and similar repositories for PaCoRe
Users that are interested in PaCoRe are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆190Updated 6 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆330Updated 7 months ago
- Scaling RL on advanced reasoning models☆661Updated 3 months ago
- MiroTrain is an efficient and algorithm-first framework research agent.☆129Updated 5 months ago
- Towards a Unified View of Large Language Model Post-Training☆198Updated 4 months ago
- ☆110Updated 4 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆225Updated 5 months ago
- 🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…☆193Updated last month
- Easy and Efficient dLLM Fine-Tuning☆203Updated last week
- A construction kit for reinforcement learning environment management.☆319Updated this week
- Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization☆307Updated 2 weeks ago
- ☆211Updated 3 weeks ago
- GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…☆318Updated 2 months ago
- Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.☆89Updated 3 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆467Updated 8 months ago
- ☆83Updated 9 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆164Updated 4 months ago
- A set of examples based on verl for end-to-end RL training recipes.☆130Updated last week
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆350Updated 2 weeks ago
- ☆379Updated 2 months ago
- Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.☆252Updated 3 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 6 months ago
- ☆207Updated this week
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆147Updated 9 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆599Updated this week
- d3LLM: Ultra-Fast Diffusion LLM 🚀☆80Updated 2 weeks ago
- A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning☆283Updated 4 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆203Updated last month
- Step-DeepResearch☆423Updated 2 weeks ago