Reinforcement Learning via Self-Distillation (SDPO)
☆822Feb 18, 2026Updated 2 months ago
Alternatives and similar repositories for SDPO
Users that are interested in SDPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reinforcement Learning from Text Feedback☆36Feb 17, 2026Updated 2 months ago
- [ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron☆30Apr 30, 2025Updated last year
- [ICLR 2026] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆45May 20, 2025Updated 11 months ago
- ☆38Mar 26, 2026Updated last month
- ☆517Apr 7, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [CVPR'26] VisPlay: Self-Evolving Vision-Language Models☆56Feb 25, 2026Updated 2 months ago
- Official Repo for Open-Reasoner-Zero☆2,093Jun 2, 2025Updated 11 months ago
- In-Context Reinforcement Learning for Tool Use in Large Language Models☆46Mar 26, 2026Updated last month
- Official Implementation of wd1☆29Sep 25, 2025Updated 7 months ago
- Repo for solving arc problems with an Neural Cellular Automata☆24Mar 9, 2026Updated last month
- The official implementation of the paper "Self-Updatable Large Language Models by Integrating Context into Model Parameters"☆15May 18, 2025Updated 11 months ago
- Image Tokenizer Needs Post-Training☆24Oct 4, 2025Updated 7 months ago
- ☆100Mar 31, 2026Updated last month
- Paper list for Efficient Reasoning.☆879Apr 21, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆127Mar 18, 2026Updated last month
- The first unified, efficient, and extensible evaluation toolkit for evaluating image generation and editing models across multiple benchm…☆43Apr 12, 2026Updated 3 weeks ago
- ☆1,135Jan 10, 2026Updated 3 months ago
- Project of ACL 2025 "UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models"☆14Mar 25, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,046Updated this week
- Official implementation of MATPO: Multi-Agent Tool-Integrated Policy Optimization.☆81Oct 31, 2025Updated 6 months ago
- Simple RL training for reasoning☆3,851Dec 23, 2025Updated 4 months ago
- [ACL 2024] ANAH & [NeurIPS 2024] ANAH-v2 & [ICLR 2025] Mask-DPO☆64Apr 30, 2025Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆143Dec 17, 2025Updated 4 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.
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆297Nov 7, 2025Updated 5 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,794May 11, 2025Updated 11 months ago
- [NeurIPS 2024] Efficiency for Free: Ideal Data Are Transportable Representations☆19Jan 19, 2025Updated last year
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆134Feb 4, 2026Updated 3 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆435Jul 11, 2025Updated 9 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆4,900Apr 6, 2026Updated 3 weeks ago
- ☆40Mar 25, 2026Updated last month
- ☆97Mar 28, 2025Updated last year
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,248Aug 27, 2025Updated 8 months ago
- 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.
- Code for Quiet-STaR☆740Aug 21, 2024Updated last year
- MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models☆43Jan 28, 2026Updated 3 months ago
- ☆14Jul 17, 2025Updated 9 months ago
- ☆50Sep 6, 2025Updated 7 months ago
- ☆359Jul 29, 2025Updated 9 months ago
- Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆56Mar 12, 2026Updated last month
- ☆30Nov 5, 2024Updated last year