arXiv News

EnglishJapanese

Switch language

EnglishJapanese
Loading account…

First-hand information for everyone

Latest
A new way to use diffusion-based denoisers inside ADMM with provable convergenceMany reported weaknesses of image-capable large language models come from bad tests and labels, not the models themselvesGreenRFM: a radiology foundation model that aims for high performance with far less computeA new way to use diffusion-based denoisers inside ADMM with provable convergenceMany reported weaknesses of image-capable large language models come from bad tests and labels, not the models themselvesGreenRFM: a radiology foundation model that aims for high performance with far less compute

Today's Briefing

Tuesday, March 17, 2026
AllArtificial IntelligenceMachine LearningNatural Language ProcessingComputer VisionRoboticsCryptographyPhysicsMathematics
Artificial IntelligenceFeatured briefing

A new way to use diffusion-based denoisers inside ADMM with provable convergence

This paper shows how to combine modern score-based generative models with a popular optimization algorithm, the alternating direction method

March 16, 2026EN2 min read
Read full article

Latest Research

Computer Vision
March 14, 2026

Many reported weaknesses of image-capable large language models come from bad tests and labels, not the models themselves

This paper looks at why multimodal large language models (MLLMs) sometimes seem worse than traditional image classifiers. MLLMs are models t

EN
2 min read
Computer Vision
March 14, 2026

GreenRFM: a radiology foundation model that aims for high performance with far less compute

This paper introduces GreenRFM, a pre-training approach for medical imaging models that focuses on using supervision more wisely instead of

EN
2 min read