arXiv News

English Japanese

Switch language

English Japanese

Loading account…

First-hand information for everyone

Latest

VLMaterial combines camera images and mmWave radar with language models to identify materials without extra trainingThinkJEPA blends a dense video predictor with a vision–language “thinker” to forecast longer-range hand movementsVLMaterial combines camera images and mmWave radar with language models to identify materials without extra trainingThinkJEPA blends a dense video predictor with a vision–language “thinker” to forecast longer-range hand movements

Today's Briefing

Friday, May 1, 2026

All Artificial Intelligence Machine Learning Natural Language Processing Computer Vision Robotics Cryptography Physics Mathematics

RoboticsFeatured briefing

VLMaterial combines camera images and mmWave radar with language models to identify materials without extra training

This paper presents VLMaterial, a system that fuses camera images and millimeter-wave (mmWave) radar with a vision-language model to identif

April 14, 2026EN2 min read

Read full article

Latest Research

Artificial Intelligence

March 24, 2026

ThinkJEPA blends a dense video predictor with a vision–language “thinker” to forecast longer-range hand movements

This paper presents ThinkJEPA, a method that combines two ways of understanding video to predict future states for tasks like hand-manipulat

2 min read