Code for the SofT-GRPO algorithm on the LLM soft-thinking reasoning pattern.
☆53Jan 2, 2026Updated 9 months ago
Alternatives and similar repositories for SofT-GRPO-master
Users that are interested in SofT-GRPO-master are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Feb 4, 2026Updated 8 months ago
- ☆67Mar 23, 2026Updated 6 months ago
- Code for [ICML2025]``Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design``.☆88May 23, 2025Updated last year
- Official implementation of Latent-SFT: teaching LLMs to reason with vocabulary-space latent chains.☆61Aug 31, 2026Updated last month
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆97Jun 29, 2026Updated 3 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ICLR'26] "Nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space" by Peihao Wang*, Ruisi Cai*, Zhen Wang, Hongyuan…☆36Mar 10, 2026Updated 7 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆390Jun 20, 2026Updated 3 months ago
- [ICLR 2026] Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization☆32Mar 6, 2026Updated 7 months ago
- Parallel Continuous Chain-of-Thought with Jacobi Iteration. Accepted to EMNLP 2025.☆25Mar 29, 2026Updated 6 months ago
- [ACL 2026 oral] SeLaR: Selective Latent Reasoning in Large Language Models☆24Apr 25, 2026Updated 5 months ago
- Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge☆135May 24, 2026Updated 4 months ago
- Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"☆109Dec 15, 2025Updated 9 months ago
- [ACL 2026] Dissecting Failure Dynamics in Large Language Model Reasoning☆19Apr 17, 2026Updated 5 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆96May 30, 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.
- Official Repository of LatentSeek☆88Jun 6, 2025Updated last year
- The official implementation of ICLR26 poster, Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs.☆18Mar 31, 2026Updated 6 months ago
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆355Jun 12, 2026Updated 4 months ago
- [ACL2026 Findings] "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models"☆20Mar 25, 2025Updated last year
- Self-Hinting Language Models Enhance Reinforcement Learning☆28Mar 28, 2026Updated 6 months ago
- [ICLR 2026] SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs☆142Aug 2, 2026Updated 2 months ago
- ☆25Feb 18, 2025Updated last year
- Learning MLPs to replace GNN☆10Jun 3, 2023Updated 3 years ago
- MCOUT: Multimodal Chain of Continuous Thought for Latent Reasoning☆22Oct 4, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Under construction☆14Jan 15, 2025Updated last year
- TAGMol: Target-Aware Gradient-guided Molecule Generation (ICML'24 ML4LMS Workshop)☆15Aug 29, 2024Updated 2 years ago
- Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning☆37Oct 26, 2025Updated 11 months ago
- ☆52Jan 30, 2026Updated 8 months ago
- ☆21May 30, 2025Updated last year
- Official implementation of the paper: [IEEE TITS] Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solve…☆16Aug 11, 2026Updated 2 months ago
- Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information☆35May 14, 2026Updated 4 months ago
- Official PyTorch implementation of our CVPR 2025 paper, "LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning."☆19Mar 28, 2025Updated last year
- Kaggle AIMO2 solution with token-efficient reasoning LLM recipes☆51Aug 7, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [CoRL 2024] Software and hardware instructions for SoniceSense.☆17Mar 1, 2025Updated last year
- ☆13Mar 26, 2026Updated 6 months ago
- Vocabulary Parallelism☆26Mar 10, 2025Updated last year
- A Python reimplementation + extension of "Planning with Large Language Models for Code Generation" (https://arxiv.org/abs/2303.05510)☆17Dec 1, 2023Updated 2 years ago
- ☆37May 29, 2025Updated last year
- EA codes from CIAM Group at SUSTech, Shenzhen, China☆21Apr 18, 2025Updated last year
- An official implementation of Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards☆36Oct 3, 2025Updated last year