[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:
- ☆28Jul 18, 2025Updated last year
- [NeurIPS 2026] POME: Post Optimization Model Edit via Muon-style Projection☆14Oct 9, 2025Updated last year
- [ICLR 2026] The official implementation of the paper “Anchored Supervised Fine-Tuning”☆51Sep 8, 2026Updated last month
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆23Aug 28, 2025Updated last year
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- 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.
- Towards a Unified View of Large Language Model Post-Training☆220Sep 8, 2025Updated last year
- ☆18Jun 10, 2025Updated last year
- ☆21Aug 25, 2026Updated 2 months ago
- ☆28Aug 31, 2025Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆476Mar 20, 2026Updated 7 months ago
- Official resources of "The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reaso…☆22Jun 13, 2025Updated last year
- ☆18Aug 4, 2025Updated last year
- NeurIPS 2025: Discriminative Constrained Optimization for Reinforcing Large Reasoning Models☆53Mar 14, 2026Updated 7 months ago
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆113Aug 15, 2025Updated last year
- 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.
- Official implementation for Text Generation Beyond Discrete Token Sampling☆26Aug 11, 2025Updated last year
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆29Apr 8, 2026Updated 6 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆455Jul 11, 2025Updated last year
- Repo for the EMNLP'24 Paper "Dual-Space Knowledge Distillation for Large Language Models". A general white-box KD framework for both same…☆66Mar 21, 2026Updated 7 months ago
- ☆27May 14, 2026Updated 5 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆104Oct 15, 2025Updated last year
- [ICML 2026] Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models☆13May 8, 2026Updated 5 months ago
- ☆68Jul 14, 2025Updated last year
- Official implementation of Selective Entropy Regularization (SIREN), proposed by paper 'Rethinking Entropy Regularization in Large Reason…☆32Dec 10, 2025Updated 10 months 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.
- Code for Probably Approximately Correct (PAC) Labels☆14Jun 13, 2025Updated last year
- ☆16Oct 2, 2022Updated 4 years ago
- [ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆928Aug 1, 2026Updated 3 months ago
- ☆14Aug 3, 2026Updated 3 months ago
- An extension of veRL for post-training LLM reasoners with on-policy self-distillation and self-distilled RLVR + the official codebase for…☆80Oct 13, 2026Updated 3 weeks ago
- Codes for Merging Large Language Models☆37Aug 7, 2024Updated 2 years ago
- Benchmark Datasets for Set Similarity Search☆12Jan 30, 2019Updated 7 years ago
- repo for paper https://arxiv.org/abs/2504.13837☆356Jul 27, 2026Updated 3 months ago
- ☆114Jun 15, 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.
- Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks☆15Feb 17, 2025Updated last year
- FAITH code and data for our WWW'24 paper "Faithful Temporal Qestion Answering over Heterogeneous Sources"☆12Oct 21, 2026Updated 2 weeks ago
- ☆13Jul 19, 2025Updated last year
- ☆43Jul 9, 2025Updated last year
- Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"☆300May 28, 2026Updated 5 months ago
- ☆13May 20, 2026Updated 5 months ago
- Orthogonal Subspace Learning for Continual Learning☆15Apr 23, 2025Updated last year