超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1
☆35Apr 5, 2025Updated last year
Alternatives and similar repositories for 24-Game-Reasoning
Users that are interested in 24-Game-Reasoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official implementation of "Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment".☆10Mar 19, 2024Updated 2 years ago
- [ EMNLP 2025 Main ] Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs☆18Nov 7, 2025Updated 11 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆29Dec 23, 2024Updated last year
- [NeurIPS 2026 Pre-to-Post] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆20Apr 16, 2026Updated 6 months ago
- Official code and dataset for our paper: RefineBench: Evaluating Refinement Capability of Language Models via Checklists☆16Dec 1, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- GET3D online data renderer☆11Dec 14, 2022Updated 3 years ago
- Policy Optimization is awesome, let’s put a tree on it! 🌲🌟☆22Jul 4, 2025Updated last year
- The official repository of the Omni-MATH benchmark.☆92Dec 22, 2024Updated last year
- ☆18Dec 11, 2025Updated 10 months ago
- 《安全多方计算——可证明安全视角》发布地址☆14May 14, 2026Updated 5 months ago
- Efficient retrieval head analysis with triton flash attention that supports topK probability☆13Jun 15, 2024Updated 2 years ago
- [NeurIPS 2025] Scaling Language-centric Omnimodal Representation Learning☆50Apr 13, 2026Updated 6 months ago
- ☆17Oct 15, 2023Updated 3 years ago
- Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner☆31Jun 27, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆11Mar 24, 2021Updated 5 years ago
- Official implementation of StableI2I （ICML 2026）☆22Aug 28, 2026Updated 2 months ago
- Some useful Blender scripts☆13Jan 15, 2025Updated last year
- Evaluating Long-Horizon Agentic Software Development Across Version Upgrades — 115 tasks, 17 repos, 5 languages☆17May 19, 2026Updated 5 months ago
- This repository includes code and materials for the paper "Efficient PRM Training Data Synthesis via Formal Verification" (ACL 2026 Findi…☆20Apr 7, 2026Updated 6 months ago
- More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression（EMNLP 2025）☆12Jan 15, 2025Updated last year
- [CVPR 2021] Learning Semantic Person Image Generation by Region-Adaptive Normalization☆51Apr 3, 2022Updated 4 years ago
- ☆13Jan 6, 2026Updated 9 months ago
- TOD-Flow: Modeling the Structure of Task-Oriented Dialogues☆13Feb 7, 2024Updated 2 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- SafeWorld: Geo-Diverse Safety Alignment (NeurIPS 2024)☆10Dec 10, 2024Updated last year
- ☆10Jul 11, 2022Updated 4 years ago
- ☆14Dec 25, 2024Updated last year
- Hacking the TGAM1 Neurosky EEG chip with an Arduino.☆12Feb 2, 2018Updated 8 years ago
- ☆10May 28, 2023Updated 3 years ago
- Dataset for the temporal memory tests☆13Jun 4, 2024Updated 2 years ago
- ☆10Jun 29, 2022Updated 4 years ago
- A Python library for calculating consensus entropy between multiple strings, particularly useful for OCR result analysis.☆15May 5, 2026Updated 5 months ago
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆16Sep 4, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code and data for EMNLP 2023 research track paper "MarkQA: A large scale KBQA dataset with numerical reasoning"☆13Jan 2, 2024Updated 2 years ago
- ☆19Sep 7, 2025Updated last year
- This is the code repository of paper "SFT Conflicts, RL Coexists"☆52Aug 4, 2026Updated 2 months ago
- A collection of metric learning papers.☆21Apr 24, 2023Updated 3 years ago
- ☆14Apr 9, 2024Updated 2 years ago
- Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognition (IJCAI 2024)☆11Aug 18, 2024Updated 2 years ago
- (ICLR 2025) AgentRefine: Enhancing Agent Generalization through Refinement Tuning☆22Nov 22, 2025Updated 11 months ago