[ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
☆64Feb 19, 2026Updated last week
Alternatives and similar repositories for RPG
Users that are interested in RPG are comparing it to the libraries listed below
Sorting:
- MB-X.01 · Logical Origin Node (L.O.N.) — TruthΩ → Co⁺ → Score⁺. Demo e spec verificabili. https://massimiliano.neocities.org/☆57Feb 3, 2026Updated 3 weeks ago
- ☆16Feb 22, 2025Updated last year
- ICML 2025 Spotlight, PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative AP…☆14Jun 27, 2025Updated 8 months ago
- ☆11May 18, 2025Updated 9 months ago
- Don't just regulate gradients like in Muon, regulate the weights too☆31Jul 30, 2025Updated 7 months ago
- ☆15Feb 26, 2025Updated last year
- ☆19Aug 4, 2025Updated 6 months ago
- SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters (ICLR 2025)☆17Aug 22, 2025Updated 6 months ago
- ☆19Jul 24, 2025Updated 7 months ago
- Official implementation of TBA for async LLM post-training.☆29Nov 5, 2025Updated 3 months ago
- ☆43Nov 1, 2025Updated 3 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆20Jun 11, 2025Updated 8 months ago
- ☆25May 7, 2025Updated 9 months ago
- QLoRA for Masked Language Modeling☆23Sep 11, 2023Updated 2 years ago
- Code for the paper: CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models☆31Apr 1, 2025Updated 10 months ago
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆41Oct 31, 2025Updated 3 months ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆39Sep 8, 2025Updated 5 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Aug 30, 2024Updated last year
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆37Feb 22, 2025Updated last year
- Official implementation of Add-SD: Rational Generation without Manual Reference.☆28Aug 19, 2024Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆141Dec 17, 2025Updated 2 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆103Aug 30, 2025Updated 5 months ago
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆29Jul 30, 2020Updated 5 years ago
- Exploitability calculation for imperfect-information game benchmarks☆33Apr 5, 2025Updated 10 months ago
- Official Code Release for "Training a Generally Curious Agent"☆45May 18, 2025Updated 9 months ago
- Make reasoning models scalable☆47May 31, 2025Updated 9 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆633Jan 29, 2026Updated last month
- Cascade Speculative Drafting☆32Apr 2, 2024Updated last year
- Ambrogio is a dev agent who tackles tech debt. Starting with automatic unit tests and docstring.☆14Mar 30, 2025Updated 11 months ago
- Read, modify and write DICOS files with python code☆13Nov 24, 2025Updated 3 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 2 months ago
- Forked from https://gitlab.com/MatejB/PrePoMax☆13Jan 8, 2024Updated 2 years ago
- ☆352Jul 29, 2025Updated 6 months ago
- Data recipes and robust infrastructure for training AI agents☆98Updated this week
- ☆39Aug 1, 2025Updated 6 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆203Jul 17, 2024Updated last year
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆411Nov 21, 2025Updated 3 months ago
- ☆93Dec 19, 2025Updated 2 months ago
- ☆32Oct 18, 2024Updated last year