This article explains the key points of RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs. 2026-09-11 (arXiv) Neau, Maëlic. Independent Researcher Paper Github Read this article in Korean Summary RelateAnything formulates relation prediction as scoring ordered region pairs from an image against an inference-time list of predicate strings, without using...

이번 글에서는 RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs 논문의 핵심 포인트만 간단히 정리한다. 2026년 9월 11일(Arxiv) Neau, Maëlic. Independent Researcher 논문 링크 Github 영문판 보기 요약 RelateAnything는 객체 클래스 라벨을 모델 입력으로 사용하지 않고, 이미지의 순서가 있는 영역 쌍과 추론 시점에 주어진 predicate 문자열 목록을 점수화하는 relation prediction...

This article explains the key points of The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement. 2026-09-10 (arXiv) Duan, Yi, Liu, Ying, Tang, Zirui, Chen, Haodong, Zhou, Jun, Liu, Yumou, Xu, Bangrui, Wu, Yukai, Chen, Sidi, Zhou, Yuhan, et al. Shanghai Jiao Tong University, Theseus Labs, Tsinghua University, ByteDance,...

이번 글에서는 The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement 논문의 핵심 포인트만 간단히 정리한다. 2026년 9월 10일(Arxiv) Duan, Yi, Liu, Ying, Tang, Zirui, Chen, Haodong, Zhou, Jun, Liu, Yumou, Xu, Bangrui, Wu, Yukai, Chen, Sidi, Zhou, Yuhan, et al. Shanghai Jiao Tong University, Theseus Labs, Tsinghua University,...

This article explains the key points of Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation. 2026-09-08 (arXiv), ACM Transactions on Graphics Pavlovic, Igor, Wandel, Thiemo, Obukhov, Anton, Bartolomei, Luca, Davydov, Andrey, Tosi, Fabio, Poggi, Matteo, Süsstrunk, Sabine, Dai, Dengxin. EPFL, Switzerland, HUAWEI Bayer Lab, Switzerland, University of Bologna, Italy...