reasoning-diffusion

KO | EN

gitlite — search

#javascript #react #ai #typescript #llm #go #android #machine-learning #rust #deep-learning #docker #windows #kubernetes #vue

reasoning-diffusion

(★ 36)

Post-trained LLaDA model with dynamic step scheduling

reasoning-diffusion 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# LLaDA-R1: Scaling Reasoning at Inference Time with Diffusion-LLMs
## Etched, Mercor, Cognition ITC Hackathon 2025

We present LLaDA-R1 (LLaDA Reasoner1), the first text diffusion model optimized for reasoning and computational efficiency at inference time. We present three key innovations: (1) a remasking optimization head that learns optimal token positions to remask at each step, (2) reinforcement learning with a dual-objective reward function balancing reasoning accuracy and computational efficiency plus a supervised fine tuning approach and (3) an adaptive diffusion method that dynamically adjusts diffusion steps based on confidence convergence. We challenge the assumption that autoregressive architectures are inherently superior for reasoning tasks and highlight the untapped potential of properly optimized diffusion-based approaches for complex problem-solving.

A preprint technical report of our work can be found below: https://docs.google.com/document/d/1fEqNj_o1NQ1_Cyc55KtH54z0jaOSyPY4agF8KRaLgqo/edit?usp=sharing.

reasoning-diffusion

reasoning-diffusion 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

reasoning-diffusion

reasoning-diffusion 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README