qwen3-base family of models RL on gsm8k using verl, is there an RL power law on downstream tasks?
☆28Oct 19, 2025Updated last year
Alternatives and similar repositories for rl-scaling-laws
Users that are interested in rl-scaling-laws are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆16Oct 24, 2021Updated 5 years ago
- [arXiv 2026] Learning from Rare Success and Rich Feedback via Reflection-Enhanced Self-Distillation☆20May 21, 2026Updated 5 months ago
- This repository contains code for the paper "Better Estimation of the KL Divergence Between Language Models"☆20May 30, 2025Updated last year
- Project code for training LLMs to write better unit tests + code☆22May 19, 2025Updated last year
- CLIPPER: Compression enables long-context synthetic data generation [COLM '25]☆11Apr 16, 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.
- PyTorch refactor of Deep Symbolic Optimization for symbolic regression and control tasks.☆28Feb 18, 2026Updated 8 months ago
- ☆15May 11, 2026Updated 5 months ago
- Scripts for training Qwen 2.5 VL with ms-swift and GRPO☆13Feb 27, 2025Updated last year
- Tillicum Onboarding & Training Materials☆13Mar 1, 2026Updated 7 months ago
- A Chrome extension to replace Arxiv URL's☆10Feb 26, 2018Updated 8 years ago
- [Lanser-CLI] Official Implementation of "Reinforcement Learning from Compiler and Language Server Feedback" (https://arxiv.org/abs/2510.2…☆18Jun 15, 2026Updated 4 months ago
- Code release for "MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning"☆11Oct 11, 2024Updated 2 years ago
- A miniature end-to-end reproduction of the Composer 2 training pipeline on a single NVIDIA GH200 480GB, using GLM-4-9B as the base model.☆15Updated this week
- Awesome tools for interpreting, manipulating the internals of of deep neural networks.☆20Oct 13, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- EMNLP 2025 "LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition"☆16Nov 4, 2025Updated 11 months ago
- This is the della guide for Zhuang's group at Princeton University.☆14Mar 24, 2026Updated 7 months ago
- Optimally-weighted herding is Bayesian Quadrature☆18Jul 8, 2016Updated 10 years ago
- ☆19Mar 10, 2026Updated 7 months ago
- An open source community implementation of VARC: "ARC Is a Vision Problem!"☆14Nov 19, 2025Updated 11 months ago
- List of papers on Self-Correction of LLMs.☆83May 19, 2026Updated 5 months ago
- ☆11Nov 16, 2019Updated 6 years ago
- It's a Simple Modern C++ Programming Style.☆10Nov 17, 2016Updated 9 years ago
- ☆11Oct 7, 2021Updated 5 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Repository for paper Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries☆13Jul 16, 2026Updated 3 months ago
- Reinforcement Learning Finetunes Small Subnetworks in Large Language Models☆15Oct 20, 2025Updated last year
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 6 months ago
- Black box application testing library/framework☆11Oct 2, 2023Updated 3 years ago
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 5 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆27Mar 2, 2026Updated 7 months ago
- ☆25Apr 30, 2026Updated 6 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆21Oct 24, 2025Updated last year
- ☆13Aug 30, 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.
- Source code for ``How far can we go without convolution: Improving fully-connected networks'' published at ICLR 2016 workshop☆13Nov 10, 2015Updated 10 years ago
- ☆12Apr 23, 2019Updated 7 years ago
- Reproducibility study of the paper: "InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information…☆12Feb 11, 2025Updated last year
- The Arcee client for executing domain-adpated language model routines https://pypi.org/project/arcee-py/☆29Oct 8, 2024Updated 2 years ago
- ☆58Aug 10, 2024Updated 2 years ago
- Scaling Offline RL via Efficient and Expressive Shortcut Models☆12Jun 18, 2025Updated last year
- Reference implementation of algorithms for reinforcement learning and Markov decision processes.☆13Jan 28, 2021Updated 5 years ago