Code for the SofT-GRPO algorithm on the LLM soft-thinking reasoning pattern.
☆53Jan 2, 2026Updated 10 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:
- Code for [ICML2025]``Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design``.☆90May 23, 2025Updated last year
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆98Jun 29, 2026Updated 4 months ago
- [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.☆397Jun 20, 2026Updated 4 months ago
- [ICLR 2026] Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization☆32Mar 6, 2026Updated 7 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.
- Official implementation of the paper "PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space"☆18May 6, 2026Updated 5 months ago
- MCOUT: Multimodal Chain of Continuous Thought for Latent Reasoning☆23Oct 4, 2025Updated last year
- Parallel Continuous Chain-of-Thought with Jacobi Iteration. Accepted to EMNLP 2025.☆27Mar 29, 2026Updated 7 months ago
- Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge☆135May 24, 2026Updated 5 months ago
- Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning☆27Feb 8, 2026Updated 8 months ago
- Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"☆111Dec 15, 2025Updated 10 months ago
- Human-AI Co-discovery system☆16Jul 2, 2026Updated 4 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
- Official Repository of LatentSeek☆88Jun 6, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A lightweight and flexible RAG (Retrieval-Augmented Generation) framework.☆11Sep 3, 2025Updated last year
- [ACL 2026] Dissecting Failure Dynamics in Large Language Model Reasoning☆19Apr 17, 2026Updated 6 months ago
- [NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning☆200Sep 15, 2025Updated last year
- Release candidate for the public Understanding ES artifact☆19Aug 31, 2026Updated 2 months ago
- [NeurIPS 2025] Official code for paper: Latent Chain-of-Thought for Visual Reasoning☆37Oct 16, 2025Updated last year
- [ACL2026 Findings] "Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models"☆20Mar 25, 2025Updated last year
- Official implementation of [NeurIPS 2024] Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification☆15May 14, 2025Updated last year
- Official Code Repo for Paper: Posterior Refinement☆14Sep 22, 2026Updated last month
- Self-Hinting Language Models Enhance Reinforcement Learning☆29Mar 28, 2026Updated 7 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.
- ☆117Jan 11, 2026Updated 9 months ago
- ☆10Dec 13, 2025Updated 10 months ago
- Harness-Delta Attribution: Dissecting Gains From Harness Evolution☆14Oct 19, 2026Updated 2 weeks ago
- Learning MLPs to replace GNN☆10Jun 3, 2023Updated 3 years ago
- [ICLR 2026] SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs☆142Aug 2, 2026Updated 3 months ago
- MCP server for AI-driven protein binder design using RFdiffusion, ProteinMPNN, ESMFold, and AlphaFold2.☆19Oct 1, 2026Updated last month
- (Nanochat based) Full-bandwidth transformer, feed LLM's own deep hidden states back to itself☆16Oct 3, 2026Updated 3 weeks ago
- Post-Trained MoE Can Skip Half Experts via Self-Distillation☆42Sep 6, 2026Updated last month
- Test-Time Anchoring for Discrete Diffusion Posterior Sampling☆11Feb 4, 2026Updated 8 months 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.
- [ICML 2023] Subgraph GNNs with best expressive power☆12Jun 19, 2023Updated 3 years ago
- Demonstrates failures of bias mitigation methods under varying types/levels of biases (WACV 2021)☆26Mar 31, 2024Updated 2 years ago
- OpenUSD Schemas for Newton☆14Updated this week
- ☆17Sep 9, 2026Updated last month
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆16Sep 4, 2026Updated last month
- ☆17Jun 18, 2026Updated 4 months ago
- Official implementation for "MarketSim: Simulating Stock Markets with Large-Scale Generative Agents (ICML'2026)"☆13Nov 27, 2025Updated 11 months ago