An opinionated atlas of post-R1 LLM post-training: RL, rewards, alignment, distillation, agents, and their connections.
☆75Oct 16, 2026Updated this week
Alternatives and similar repositories for llm-post-training-atlas
Users that are interested in llm-post-training-atlas 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 implementation for CIKM 2024: Towards Completeness-Oriented Tool Retrieval for Large Language Models.☆27Nov 6, 2024Updated last year
- ☆20May 14, 2025Updated last year
- [ICLR 2026] PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, co…☆40Sep 9, 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 5 months ago
- ☆14May 12, 2025Updated last year
- 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.
- ☆28Aug 31, 2025Updated last year
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆22Aug 28, 2025Updated last year
- ☆30Nov 5, 2024Updated last year
- Model merging is a highly efficient approach for long-to-short reasoning.☆104Oct 15, 2025Updated last year
- ☆12Sep 1, 2023Updated 3 years ago
- LLM-MapBook: AI-Powered Maps for Storytelling. Extracts geo-coordinates from books, visualizes on interactive maps, offering immersive st…☆10Aug 27, 2024Updated 2 years ago
- Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking☆17Oct 26, 2023Updated 2 years ago
- ☆21Apr 21, 2026Updated 5 months ago
- 用Paddle复现Recipes for building an open-domain chatbot论文☆11Nov 1, 2021Updated 4 years 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.
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated 2 years ago
- ☆37Jan 20, 2026Updated 8 months ago
- ☆15Jan 14, 2026Updated 9 months ago
- Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 …☆40May 31, 2025Updated last year
- Official implementation of "Can Test-Time Scaling Improve World Foundation Model?"☆15Jul 12, 2025Updated last year
- Text generation using language models with multiple exit heads☆16Oct 11, 2026Updated last week
- 2024广西数字开放创新应用大赛，多模态新闻谣言分类☆18Jan 18, 2025Updated last year
- o1 Chain of Thought Examples☆33Oct 4, 2024Updated 2 years ago
- 古籍解读大模型是基于InternLM2-7B的一款辅助学习工具，专为帮助用户理解和欣赏中国古代文学和文化而设计。 它具备古诗赏析、文言文翻译、成语解释、《论语》注释以及《百家姓》解读等功能，使用户能够深入领会古代诗词、文献、成语典故和姓氏文化的精髓，是学术研究者、学生以及所…☆16May 26, 2026Updated 4 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.
- SMART introduces a novel test-time framework where Small Language Models (SLMs) reason step-by-step, and Large Language Models (LLMs) pro…☆12Jul 9, 2025Updated last year
- Documentation at☆14Mar 27, 2025Updated last year
- Claude Code skill for rigorous academic paper writing, revision, and submission. Field-agnostic with per-paper journal overrides.☆108Updated this week
- Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends [NeurIPS 2023]☆10Jan 28, 2024Updated 2 years ago
- Artifact evaluation for HPCA'24 paper Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accele…☆11Mar 3, 2024Updated 2 years ago
- ☆33Jun 24, 2024Updated 2 years ago
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆15Apr 8, 2025Updated last year
- Yet another frontend for LLM, written using .NET and WinUI 3☆11Sep 14, 2025Updated last year
- ☆203Updated this week
- 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.
- [AAAI 2025] Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks☆13Jun 19, 2025Updated last year
- A Survey of Direct Preference Optimization (DPO)☆94Jul 4, 2025Updated last year
- Paper Insight - AI驱动的学术论文智能分析☆138Aug 13, 2026Updated 2 months ago
- source code for ICLR'24 paper "How does unlabeled data provably help OOD detection?"☆14Feb 1, 2024Updated 2 years ago
- [ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLM…☆69Oct 27, 2024Updated last year
- ☆14May 4, 2026Updated 5 months ago
- ☆11Oct 11, 2023Updated 3 years ago