Accelerating RL for LLM Reasoning with Optimal Advantage Regression
☆41May 30, 2025Updated last year
Alternatives and similar repositories for A-PO
Users that are interested in A-PO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A simple implementation of ReasonGenRM.☆19Apr 21, 2025Updated last year
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆25Oct 8, 2024Updated last year
- Reinforcement Learning via Regressing Relative Rewards☆40Dec 12, 2024Updated last year
- soft entropy estimation☆16May 29, 2026Updated 2 months ago
- Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)☆59Nov 8, 2024Updated last year
- 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.
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 3 months ago
- ☆82Jun 8, 2026Updated 2 months ago
- Learning from Mixed Rollouts: Logit Fusion as a Bridge Between Imitation and Exploration☆17Feb 24, 2026Updated 5 months ago
- ☆22Jun 4, 2025Updated last year
- ☆31Mar 2, 2023Updated 3 years ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆32Jun 16, 2024Updated 2 years ago
- Arbitrary Entropy Policy Optimization: Entropy Is Controllable in Reinforcement Fine-tuning☆17Jan 19, 2026Updated 6 months ago
- Official implementation of TBA for async LLM post-training.☆32Nov 5, 2025Updated 9 months ago
- [TACL, EMNLP 2025 Oral] Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Thr…☆36Dec 5, 2025Updated 8 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ICLR 2026] Quantile Advantage Estimation for Entropy-Safe Reasoning☆29Oct 14, 2025Updated 9 months ago
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆32Jan 10, 2026Updated 7 months ago
- Fully open reproduction of DeepSeek-R1☆11Mar 24, 2025Updated last year
- ☆15Apr 26, 2025Updated last year
- 集中管理所有的prompt。☆14Nov 27, 2024Updated last year
- 🖖 图谱式笔记系统，旨在提高个人笔记的使用率！☆11Jan 17, 2021Updated 5 years ago
- Code for PuzzleJAX, a benchmark for reasoning and learning, that reimplements PuzzleScript, a concise and expressive DSL and game engine …☆29Aug 4, 2026Updated last week
- A Deep Reinforcement Learning Strategy and Framework for Floating Waste Capture☆13Mar 13, 2025Updated last year
- This repository contains code for the paper "Better Estimation of the KL Divergence Between Language Models"☆19May 30, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆34Oct 8, 2025Updated 10 months ago
- ☆16Apr 30, 2024Updated 2 years ago
- Evaluating LLMs' abilities to generate structural output [TMLR2025]☆23Jul 26, 2026Updated 2 weeks ago
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year
- [ICML2026] Reproduce Kimi K1.5/K2 RL algorithm and rollout system☆19Apr 9, 2026Updated 4 months ago
- Scaling RL on advanced reasoning models☆692Oct 20, 2025Updated 9 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆78Aug 17, 2024Updated last year
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆76Jun 29, 2026Updated last month
- uncertainty-guided matting on ICML2023☆12Aug 3, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆146Oct 27, 2024Updated last year
- ☆90Aug 16, 2025Updated 11 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models☆79Oct 16, 2024Updated last year
- Code for ICRA'25 paper: "Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments"☆16Apr 2, 2025Updated last year
- ☆14Aug 3, 2022Updated 4 years ago
- R3: Robust Rubric-Agnostic Reward Models☆23Jul 12, 2025Updated last year