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:
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆25Oct 8, 2024Updated 2 years ago
- Value model for block-wise search☆14Jul 1, 2025Updated last year
- Code for "On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding (ICML 2025)"☆10Jun 29, 2025Updated last year
- Mitigating the Filter Bubble while Maintaining Relevance: Targeted Diversification with VAE-based Recommender Systems☆10Mar 15, 2023Updated 3 years ago
- A simple implementation of ReasonGenRM.☆19Apr 21, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Reinforcement Learning via Regressing Relative Rewards☆40Dec 12, 2024Updated last year
- soft entropy estimation☆17May 29, 2026Updated 5 months ago
- ☆84Jun 8, 2026Updated 4 months ago
- Code and data for the paper FROM ATOMIC TO COMPOSITE: REINFORCEMENT LEARNING ENABLES GENERALIZATION IN COMPLEMENTARY REASONING☆15Oct 15, 2026Updated 3 weeks ago
- ☆21Nov 13, 2023Updated 2 years ago
- ☆32May 20, 2026Updated 5 months ago
- Code for SFT and RL☆12Jun 22, 2025Updated last year
- The official code release for Q#: Provably Optimal Distributional RL for LLM Post-Training☆21Mar 4, 2025Updated last year
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Optimizing Review Generation Through Prompt Generation☆17Apr 15, 2024Updated 2 years ago
- Learning from Mixed Rollouts: Logit Fusion as a Bridge Between Imitation and Exploration☆18Feb 24, 2026Updated 8 months ago
- Official repo for our AAAI'21 paper, https://arxiv.org/abs/2007.12354☆30Jul 14, 2021Updated 5 years ago
- Code for the paper Depth Memory☆15Oct 14, 2026Updated 3 weeks ago
- ☆31Mar 2, 2023Updated 3 years ago
- ⚡ Official code for “Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus”…☆25Aug 13, 2026Updated 2 months ago
- Code for "Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation"☆19Sep 1, 2026Updated 2 months ago
- Stable and Quantitative Control of Policy Entropy in RL Post-Training☆18Updated this week
- 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
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official implementation of TBA for async LLM post-training.☆32Nov 5, 2025Updated 11 months ago
- ☆15Apr 26, 2025Updated last year
- Official implementation of AffordBot: 3D Fine-Grained Embodied Reasoning via Multimodal Large Language Models☆15Dec 4, 2025Updated 11 months ago
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated last month
- [ICLR 2026] Quantile Advantage Estimation for Entropy-Safe Reasoning☆29Oct 14, 2025Updated last year
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆32Jan 10, 2026Updated 9 months ago
- ☆13Apr 20, 2025Updated last year
- Near-linear attention in theory and practice☆13Aug 10, 2026Updated 2 months ago
- 🖖 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
- 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.
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆55Jun 16, 2024Updated 2 years ago
- ☆16Jul 21, 2025Updated last year
- Official repository of the paper: Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code (Findings of EACL …☆12Mar 26, 2026Updated 7 months ago
- ☆30Jan 31, 2026Updated 9 months ago
- ☆16Apr 30, 2024Updated 2 years ago
- ☆10Sep 10, 2023Updated 3 years ago
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year