Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
☆27Feb 8, 2026Updated 9 months ago
Alternatives and similar repositories for Scaf-GRPO
Users that are interested in Scaf-GRPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Oct 9, 2025Updated last year
- Self-Hinting Language Models Enhance Reinforcement Learning☆30Mar 28, 2026Updated 7 months ago
- ☆14Jan 23, 2026Updated 9 months ago
- The source code of "DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models"☆11Oct 18, 2026Updated last month
- Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"☆117Sep 14, 2026Updated 2 months ago
- 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.
- [NeurIPS 2024] | An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding☆23Oct 10, 2024Updated 2 years ago
- Code for paper - A Deep Generative Approach to Conditional Sampling☆13Apr 24, 2022Updated 4 years ago
- [ICML 2026 Spotlight] Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback☆76Jun 3, 2026Updated 5 months ago
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated 2 years ago
- 实体链接过程中的一些相关代码☆10Jun 13, 2018Updated 8 years ago
- ☆16Sep 4, 2025Updated last year
- ☆62Jul 21, 2025Updated last year
- The implementation of ACL 2026 paper "Rethinking entropy interventions in rlvr: An entropy change perspective"☆29Oct 15, 2026Updated last month
- Benchmarking Multi-Image Understanding in Vision and Language Models☆12Jul 29, 2024Updated 2 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.
- Mechanistic interpretability in IR☆15Oct 16, 2026Updated last month
- ☆16May 30, 2025Updated last year
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆17Jul 18, 2024Updated 2 years ago
- ☆22Jan 2, 2026Updated 10 months ago
- Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversation…☆12Nov 23, 2023Updated 2 years ago
- [paper][ACL 2026 main] Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning☆12Apr 8, 2026Updated 7 months ago
- ☆15Nov 6, 2022Updated 4 years ago
- Hearst Patterns to extract Hypernyms from text☆12Oct 30, 2019Updated 7 years ago
- [CVPR26] Discriminative Perception via Anchored Description for Reasoning Segmentation☆11Apr 6, 2026Updated 7 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.
- ☆46Sep 17, 2026Updated 2 months ago
- Official implementation of "MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning"☆11Aug 23, 2025Updated last year
- [ACL'26 Main] Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement☆13Apr 6, 2026Updated 7 months ago
- [NeurIPS 2025] MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks☆67Sep 4, 2026Updated 2 months ago
- Exercises and Projects I've worked on in the "Building Java Programs: A Back to Basics Approach" book by Marty Stepp and Stuart Reges☆10Feb 14, 2018Updated 8 years ago
- SDPG: Self-Distilled Policy Gradient☆56Jun 15, 2026Updated 5 months ago
- Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"☆12Jul 25, 2024Updated 2 years ago
- ☆39Nov 18, 2025Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- 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.
- Latency-aware dynamic robot manipulation benchmark built on all 40 LIBERO tasks☆13Nov 5, 2026Updated 2 weeks ago
- ☆14Oct 11, 2023Updated 3 years ago
- Code example for pretraining an LLM with vanilla PyTorch training loop☆10Jun 6, 2024Updated 2 years ago
- Code implementation for ICLR 2025 paper: ELFS: Label-Free Coreset Selection with Proxy Training Dynamics☆13Feb 11, 2025Updated last year
- ☆14Sep 15, 2025Updated last year
- Block-GTQ: RoPE-aware bit allocation for KV-cache quantization☆17Oct 29, 2026Updated 3 weeks ago
- ✅ Predicting LLM correctness from model internals☆11Apr 20, 2026Updated 6 months ago
Are these results useful?