Official implementation of Latent-SFT: teaching LLMs to reason with vocabulary-space latent chains.
☆61Aug 31, 2026Updated 3 weeks ago
Alternatives and similar repositories for Latent-SFT
Users that are interested in Latent-SFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of Latent-GRPO: reinforcement learning for vocabulary-space latent reasoning.☆21Aug 31, 2026Updated 3 weeks ago
- Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"☆109Dec 15, 2025Updated 9 months ago
- ☆25Feb 18, 2025Updated last year
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆96Jun 29, 2026Updated 2 months ago
- Parallel Continuous Chain-of-Thought with Jacobi Iteration. Accepted to EMNLP 2025.☆26Mar 29, 2026Updated 5 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.
- Code for the SofT-GRPO algorithm on the LLM soft-thinking reasoning pattern.☆53Jan 2, 2026Updated 8 months ago
- ☆57Oct 23, 2025Updated 11 months ago
- ☆17Feb 4, 2026Updated 7 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
- ☆29Aug 8, 2025Updated last year
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆353Jun 12, 2026Updated 3 months ago
- Official implementation for Text Generation Beyond Discrete Token Sampling☆26Aug 11, 2025Updated last year
- Official implementation of the paper "Pretraining Language Models to Ponder in Continuous Space"☆27Jul 21, 2025Updated last year
- Official codebase for the paper Latent Visual Reasoning☆184Oct 22, 2025Updated 11 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆385Jun 20, 2026Updated 3 months ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆65Apr 6, 2025Updated last year
- [ICLR 2026] SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs☆141Aug 2, 2026Updated last month
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆165Jun 22, 2026Updated 3 months ago
- 揣摩研习社关注自然语言和信息检索前沿技术,解读热门科技论文,分享实用科研工具,挖掘人工智能冰山之下的学术和应用价值!☆37Nov 4, 2022Updated 3 years ago
- Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge☆135May 24, 2026Updated 4 months ago
- MCOUT: Multimodal Chain of Continuous Thought for Latent Reasoning☆22Oct 4, 2025Updated 11 months ago
- [ACM MM2026] This is the official implementation of MedCCO☆17Jul 12, 2026Updated 2 months ago
- [ICML'26] Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"☆85Jul 17, 2026Updated 2 months 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.
- [ICLR 2026] Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization☆32Mar 6, 2026Updated 6 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆105Dec 19, 2024Updated last year
- A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling☆15Dec 5, 2023Updated 2 years ago
- [ICLR 2026] Official repository for the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"☆36Oct 28, 2025Updated 11 months ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,711Jul 2, 2026Updated 2 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 6 months ago
- Paper list for Efficient Reasoning.☆906May 29, 2026Updated 3 months ago
- This is the official code for our paper "Simple and Scalable Nearest Neighbor Machine Translation" (ICLR 2023).