d1

Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

CommonProductProductivityReasoningReinforcement Learning

Visit

This model improves the reasoning capabilities of diffusion large language models through reinforcement learning and masked self-supervised fine-tuning with high-quality reasoning trajectories. The importance of this technology lies in its ability to optimize the model's reasoning process, reduce computational costs, while ensuring the stability of learning dynamics. Suitable for users who want to improve efficiency in writing and reasoning tasks.

Product Finder

Product Submit

AI Models Finder

MCP Servers

MCP Client

MCP Inspector

Case Tutorials

Latest AI News

AI Daily Brief

d1

d1 Visit Over Time

d1 Visit Trend

d1 Visit Geography

d1 Traffic Sources

d1 Alternatives

d1 — Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

EurusPRM-Stage2 — EurusPRM-Stage2 is a reinforcement learning model based on implicit process rewards aimed at enhancing the reasoning capabilities of generative models.

DeepSeek-R1-Distill-Llama-70B — DeepSeek-R1-Distill-Llama-70B is a large language model optimized using reinforcement learning, focusing on reasoning and conversational capabilities.

Kimi k1.5 — Kimi k1.5 is a multimodal language model enhanced by reinforcement learning, focused on improving reasoning and logical abilities.

HunYuan T1 — The industry's first ultra-large-scale hybrid Mamba reasoning model, with strong reasoning capabilities.

PRIME-RL — PRIME enhances the reasoning abilities of language models through implicit reward-driven online reinforcement learning.

DeepSeek-R1-Distill-Qwen-7B — DeepSeek-R1-Distill-Qwen-7B is an open-source reasoning model focusing on mathematics, coding, and reasoning tasks.

HuatuoGPT-o1 — A large language model for complex reasoning in the medical field

DIAMOND — A reinforcement learning agent trained in a diffusion world model

EurusPRM-Stage1 — EurusPRM-Stage1 is a reinforcement learning model based on implicit process rewards, aimed at enhancing the reasoning abilities of generative models.

mwp_ReFT — A deep reinforcement learning-based model fine-tuning framework

Search-R1 — A highly efficient reinforcement learning framework for training language models that perform reasoning and call search engines.

Steiner-32b-preview — Steiner is a reasoning model trained on synthetic data, designed to explore multiple reasoning paths and verify them autonomously.

HunYuan T1 — An industry-leading deep reasoning large model, optimized for human preferences.

GLM-Zero-Preview — Zhizhu's deep reasoning model is proficient in mathematical logic and code reasoning.

SERL — SERL is an efficient robot reinforcement learning software suite

SWE-RL — Enhancing the reasoning capabilities of large language models in open-source software evolution through reinforcement learning.

DiffusionRL — Large-scale Reinforcement Learning for Diffusion Models

AlphaMaze — AlphaMaze is a decoder language model focused on visual reasoning tasks, designed to address the limitations of traditional language models in visual tasks.

Unitree RL GYM — Unitree robot platform for reinforcement learning

Eurus-2-7B-PRIME — A 7B parameter language model trained based on the PRIME methodology, specifically designed to enhance reasoning capabilities.

agibot_x1_train — Modular humanoid robot for reinforcement learning training

Fin-R1 — A large language model for financial reasoning driven by reinforcement learning.

RLVR-GSM-MATH-IF-Mixed-Constraints — A dataset of math problems for reinforcement learning validation.

JaxMARL — JaxMARL - A multi-agent reinforcement learning library

ReFT — ReFT enhances the reasoning ability of LLM

R1-Omni — R1-Omni is a full-modality emotion recognition model incorporating reinforcement learning, focusing on improving the interpretability of multimodal emotion recognition.

Light-R1-14B-DS — An open-source 14B-parameter mathematical model, trained using reinforcement learning, with excellent performance.

DigiRL — Train outdoor device control agents using autonomous reinforcement learning

DeepScaleR-1.5B-Preview — A large language model optimized by reinforcement learning, focusing on enhancing mathematical problem-solving skills.