Gorio Tech Blog search

Recursive Language Models | Summary

EN 31 Dec 2025 | Paper Review Recursive Language Models Long-Context Language Models Test-Time Scaling Supervised Fine-Tuning

This article explains the key points of Recursive Language Models. 2025-12-31 (arXiv), Preprint Zhang, Alex L., Kraska, Tim, Khattab, Omar. MIT CSAIL Paper Read this article in Korean Summary Recursive Language Models proposes an inference framework that stores the user prompt in an external programming environment rather than placing it...

Comment  Read more

Recursive Language Models 요약 설명

KO 31 Dec 2025 | Paper Review Recursive Language Models Long-Context Language Models Test-Time Scaling Supervised Fine-Tuning

이번 글에서는 Recursive Language Models 논문의 핵심 포인트만 간단히 정리한다. 2025년 12월 31일(Arxiv), Preprint Zhang, Alex L., Kraska, Tim, Khattab, Omar. MIT CSAIL 논문 링크 영문판 보기 요약 Recursive Language Models는 사용자 프롬프트를 기반 LLM의 컨텍스트 윈도에 직접 넣지 않고 외부 프로그래밍 환경에 저장하는 추론 프레임워크를 제안한다. 모델은 코드를 작성해...

Comment  Read more

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation | Summary

EN 31 Dec 2025 | Paper Review Text-to-Video Generation Direct Preference Optimization Physical Reasoning

This article explains the key points of PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation. 2025-12-31 (arXiv) Cai, Yuanhao, Li, Kunpeng, Jia, Menglin, Wang, Jialiang, Sun, Junzhe, Liang, Feng, Chen, Weifeng, Juefei-Xu, Felix, Wang, Chu, Thabet, Ali, et al. Meta Superintelligence Labs, Johns Hopkins University, Meta BizAI,...

Comment  Read more

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation 요약 설명

KO 31 Dec 2025 | Paper Review Text-to-Video Generation Direct Preference Optimization Physical Reasoning

이번 글에서는 PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation 논문의 핵심 포인트만 간단히 정리한다. 2025년 12월 31일(Arxiv) Cai, Yuanhao, Li, Kunpeng, Jia, Menglin, Wang, Jialiang, Sun, Junzhe, Liang, Feng, Chen, Weifeng, Juefei-Xu, Felix, Wang, Chu, Thabet, Ali, et al. Meta Superintelligence Labs, Johns Hopkins University, Meta...

Comment  Read more

mHC: Manifold-Constrained Hyper-Connections | Summary

EN 31 Dec 2025 | Paper Review Residual Connections Hyper-Connections LLM Pretraining

This article explains the key points of mHC: Manifold-Constrained Hyper-Connections. 2025-12-31 (arXiv) Xie, Zhenda, Wei, Yixuan, Cao, Huanqi, Zhao, Chenggang, Deng, Chengqi, Li, Jiashi, Dai, Damai, Gao, Huazuo, Chang, Jiang, Yu, Kuai, et al. DeepSeek-AI Paper Read this article in Korean Summary mHC: Manifold-Constrained Hyper-Connections addresses the instability and memory-access...

Comment  Read more