📄Score Centering Stabilizes Off-policy Reinforcement Learning
☆229Oct 27, 2026Updated last week
Alternatives and similar repositories for score-centering
Users that are interested in score-centering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆27Aug 17, 2026Updated 2 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆455Jul 11, 2025Updated last year
- ☆27Oct 8, 2026Updated 3 weeks ago
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example☆98Sep 4, 2026Updated 2 months ago
- ☆13Sep 29, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆22Oct 7, 2026Updated 3 weeks ago
- P1: Mastering Physics Olympiads with Reinforcement Learning☆91Dec 29, 2025Updated 10 months ago
- Reinforcement Learning via Self-Distillation (SDPO)☆1,143Jul 1, 2026Updated 4 months ago
- slime is an LLM training framework for RL Scaling.☆8,802Updated this week
- Stabilizing PPO in LLM post-training via robust critic learning https://arxiv.org/pdf/2609.36802☆25Updated this week
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆300May 28, 2026Updated 5 months ago
- ☆43Aug 21, 2026Updated 2 months ago
- Weak-to-Strong Generalization via Direct On-Policy Distillation☆97Aug 18, 2026Updated 2 months ago
- Code of the research paper "SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm"☆14Jul 8, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆29May 17, 2026Updated 5 months ago
- The official code implement of <Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima>☆19Jun 17, 2026Updated 4 months ago
- A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).☆1,218Updated this week
- [Tech Report] Context Scaling: Scaling Properties of Text Conditioning in Visual Generation☆190Aug 7, 2026Updated 2 months ago
- ☆18May 27, 2026Updated 5 months ago
- Learning Native Reflection in Unified Models: reflection SFT and multi-round Flow-GRPO RL for BAGEL☆33Oct 20, 2026Updated 2 weeks ago
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated last month
- Extract deeplinks, shortcuts, and external entry points from Android APK/XAPK files.☆13May 11, 2026Updated 5 months ago
- Reconstructing Big Tech T2I/T2V captioning pipelines for production and research☆45Aug 5, 2026Updated 3 months 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.
- [TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe☆1,066Aug 20, 2026Updated 2 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆751Oct 19, 2026Updated 2 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,274Updated this week
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆730Sep 24, 2025Updated last year
- RL-training knowledge-work agents on APEX-Agents data with SkyRL + Harbor☆224Sep 1, 2026Updated 2 months ago
- ☆131Updated this week
- SPADE: Self-Play in Adaptive Synthetic Executable Environments☆128Updated this week
- ☆370Jul 29, 2025Updated last year
- ☆89May 12, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.☆459Aug 27, 2026Updated 2 months ago
- Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge☆135May 24, 2026Updated 5 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆56Oct 29, 2024Updated 2 years ago
- Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation☆118Aug 20, 2026Updated 2 months ago
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 6 months ago
- ☆19Apr 5, 2025Updated last year
- [ICML'26] Toward Human-like Audio-Visual Intelligence of Omni-MLLMs☆18Oct 4, 2026Updated last month