[ICLR 2026] PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, constraining policy drift to stabilize training and improve generalization.
☆40Sep 9, 2025Updated last year
Alternatives and similar repositories for PSFT
Users that are interested in PSFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] The official implementation of the paper “Anchored Supervised Fine-Tuning”☆50Sep 8, 2026Updated 2 weeks ago
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆22Aug 28, 2025Updated last year
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- ☆111Jul 6, 2026Updated 2 months ago
- ☆17Jun 10, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Towards a Unified View of Large Language Model Post-Training☆219Sep 8, 2025Updated last year
- ☆18Aug 4, 2025Updated last year
- ☆16Jan 16, 2023Updated 3 years ago
- [ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆1,035Aug 1, 2026Updated last month
- NeurIPS 2025: Discriminative Constrained Optimization for Reinforcing Large Reasoning Models☆53Mar 14, 2026Updated 6 months ago
- DCPO: Dynamic Adaptive Clipping for RL☆50Apr 1, 2026Updated 5 months ago
- dUltra: Ultra-Fast Diffusion Large Language Models via Reinforcement Learning☆18Jul 11, 2026Updated 2 months ago
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆112Aug 15, 2025Updated last year
- Official implementation for Text Generation Beyond Discrete Token Sampling☆26Aug 11, 2025Updated last year
- 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.
- [ECCV2024] Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models☆20Jul 17, 2024Updated 2 years ago
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆29Apr 8, 2026Updated 5 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆453Jul 11, 2025Updated last year
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆25May 6, 2026Updated 4 months ago
- ☆34Jan 17, 2025Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- Model merging is a highly efficient approach for long-to-short reasoning.☆104Oct 15, 2025Updated 11 months ago
- ☆68Jul 14, 2025Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆471Mar 20, 2026Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official implementation of Selective Entropy Regularization (SIREN), proposed by paper 'Rethinking Entropy Regularization in Large Reason…☆32Dec 10, 2025Updated 9 months ago
- ☆114Jun 15, 2025Updated last year
- ☆16Mar 6, 2025Updated last year
- ☆37Feb 12, 2026Updated 7 months ago
- JoinAI是一个开源仓库，专注于算法工程能力的培养，包括工程和数学原理的整理☆11Apr 20, 2025Updated last year
- The Search for Sparse, Robustness Neural Networks☆11Mar 24, 2023Updated 3 years ago
- ☆16Sep 8, 2025Updated last year
- [ICLR 2022] Denoising Likelihood Score Matching for Conditional Score-based Data Generation☆12Jun 15, 2026Updated 3 months ago
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆96Jan 29, 2026Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official implementation of "Can Test-Time Scaling Improve World Foundation Model?"☆15Jul 12, 2025Updated last year
- PeRL: Parameter-Efficient Reinforcement Learning☆83May 20, 2026Updated 4 months ago
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆105Jun 16, 2025Updated last year
- Official codebase for "Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions" (Matrenok …☆30Dec 8, 2025Updated 9 months ago
- Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function☆13Apr 13, 2026Updated 5 months ago
- Code for Generalization Guarantees for (Multi-Modal) Imitation Learning☆11Jul 14, 2022Updated 4 years ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year