Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
☆15Jun 28, 2025Updated last year
Alternatives and similar repositories for Trust-Region-Preference-Approximation
Users that are interested in Trust-Region-Preference-Approximation are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This repository collects various works that reproduce DeepSeek R1, as well as works related to DeepSeek R1 and the DeepSeek series.☆20Updated this week
- ☆20Feb 26, 2021Updated 5 years ago
- Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design☆20Jul 26, 2023Updated 3 years ago
- Extend bert-nmt to context-aware translation.☆11May 24, 2021Updated 5 years ago
- ACL19_Depth_Growing_for_Neural_Machine_Translation☆23Jul 6, 2019Updated 7 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- M-CURL: Masked Contrastive Representation Learning for Reinforcement Learning☆29Nov 5, 2020Updated 5 years ago
- ☆14Mar 2, 2023Updated 3 years ago
- MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer (EMNLP 2025)☆12Apr 18, 2025Updated last year
- MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)☆37Jul 16, 2025Updated last year
- Codebase for the paper "A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language"☆11Oct 11, 2024Updated 2 years ago
- Implementation for the paper "Incentivizing LLMs to Self-Verify Their Answers"☆20Dec 23, 2025Updated 10 months ago
- simple demo codes for Learning to Teach with Dynamic Loss Functions☆17Oct 22, 2019Updated 7 years ago
- [CVPR 2026 Fingdings] This repo is the official implementation of "Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision‑La…☆28Mar 15, 2026Updated 7 months ago
- A dual learning toolkit developed by Microsoft Research☆74Jun 12, 2023Updated 3 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.
- Unified 2D and 3D Pre-Training of Molecular Representations☆30Jun 30, 2022Updated 4 years ago
- code for π-Light (AAAI2024)☆12Dec 13, 2023Updated 2 years ago
- ☆16Sep 4, 2025Updated last year
- ☆13Nov 11, 2025Updated 11 months ago
- ☆15Jun 13, 2025Updated last year
- Extracting Predictive Representations from Transformer-based models.☆12Jun 15, 2026Updated 4 months ago
- ☆32Jan 13, 2025Updated last year
- This is the repository for USTC-MSRA 2023 Innovation Project, with the topic of Dynamic Simulation.☆10Aug 30, 2023Updated 3 years ago
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆78Jun 29, 2026Updated 4 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.
- Pytorch Implementation of PRISM-VQ☆18Aug 19, 2026Updated 2 months ago
- ☆47Jun 20, 2025Updated last year
- [ICLR 2026] Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs☆19Nov 25, 2025Updated 11 months ago
- ☆46Oct 28, 2025Updated last year
- [ACL'24 Findings] Official code for "TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback"☆12Dec 6, 2024Updated last year
- The official implementation of dual-view molecule pre-training.☆44Nov 22, 2021Updated 4 years ago
- Dateset Reset Policy Optimization☆30Apr 12, 2024Updated 2 years ago
- ☆15May 27, 2025Updated last year
- ☆16May 27, 2021Updated 5 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Codebase for the rational policy gradient algorithm and paper.☆13Nov 13, 2025Updated 11 months ago
- ☆18Mar 2, 2026Updated 8 months ago
- Official code for ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning (AAAI'24)☆16Feb 10, 2024Updated 2 years ago
- Soft Mixture of Experts Vision Transformer, addressing MoE limitations as highlighted by Puigcerver et al., 2023.☆16Aug 13, 2023Updated 3 years ago
- ☆21Jul 26, 2026Updated 3 months ago
- 在线编辑pdf文档☆11Jun 21, 2022Updated 4 years ago
- The official code for PDVN: Retrosynthetic Planning with Dual Value Networks (ICML 2023)☆34Apr 21, 2024Updated 2 years ago