공대생 도전 일지

LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal

https://arxiv.org/abs/2601.04768 LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity RemovalDense retrieval in multilingual settings often searches over mixed-language collections, yet multilingual embeddings encode language identity alongside semantics. This language signal can inflate similarity for same-language pairs and crowd out relevant evarxiv.org..

NaviAgent, AGENTORCHESTRA

https://arxiv.org/abs/2506.19500 NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale OrchestrationLarge language models (LLMs) have recently demonstrated the ability to act as function call agents by invoking external tools, enabling them to solve tasks beyond their static knowledge. However, existing agents typically call tools step by step at a timearxiv.org ICLR 2026에도 제출된 것 ..

AI Agent Orchestrator, 오케스트레이션

https://www.ibm.com/kr-ko/think/topics/ai-agent-orchestration AI 에이전트 오케스트레이션이란 무엇인가요? | IBMAI 에이전트 오케스트레이션이 통합 시스템 내에서 여러 전문화된 AI 에이전트를 조정하여 복잡한 목표를 효율적으로 달성하는 방법을 알아보세요.www.ibm.com 에이전트 오케스트레이션 - 여러 전문화된 AI Agent를 조정하여 목표를 달성단일 범용 AI 솔루션에 의존하는게 아니라 특정 작어을 위해 설계된(혹은 스스로 설계하여) AI 에이전트 네트워크를 사용하여 복잡한 워크플로와 프로세스를 자동화 함 AI 시스템이 발전하면서 Agent로도 복잡한 작업을 처리하기에 충분하지 않은 경우가 많고, 자율 시스템은 여러 클라우드와 어플리케이션에 걸..

https://arxiv.org/abs/2511.21689 ToolOrchestra: Elevating Intelligence via Efficient Model and Tool OrchestrationLarge language models are powerful generalists, yet solving deep and complex problems such as those of the Humanity's Last Exam (HLE) remains both conceptually challenging and computationally expensive. We show that small orchestrators managing other modelarxiv.orgNVIDIA 논문입니다.기존 LLM의..

2025.12.06 - [인공지능/논문 리뷰 or 진행] - Privacy AI 관련 조사 5 Privacy AI 관련 조사 5조금은 이제 알 것 같은....https://aclanthology.org/2025.acl-long.58/ ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion AttacksYu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyoonschallenge.tistory.com논문 작성 중이라 바빠서 오랜만에 적어보네요 User의 Prompt를 보호하기 위해 다양한 프라이버시 보호 방법이..

2025.12.08 - [인공지능/논문 리뷰 or 진행] - 세부 정리 - PrivacyRestore 세부 정리 - PrivacyRestorehttps://aclanthology.org/2025.acl-long.532/ PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and RestorationZiqian Zeng, Jianwei Wang, Junyao Yang, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen. Proceedings of tyoonschallenge.tistory.com 실험이 좀 다양하게 진행된 것 같아서 하나 하나 까보려고 합니다...

https://aclanthology.org/2025.acl-long.532/ PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and RestorationZiqian Zeng, Jianwei Wang, Junyao Yang, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.aclanthology.orgACL 2025에 붙은 논문입니다. LLM ..

https://arxiv.org/abs/2309.15649 Generative Speech Recognition Error Correction with Large Language Models and Task-Activating PromptingWe explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evarxiv...

일단 기말고사가 닥쳐와서.... https://docs.pytorch.org/docs/stable/generated/torch.nn.CTCLoss.html CTCLoss — PyTorch 2.9 documentationCTCLoss class torch.nn.CTCLoss(blank=0, reduction='mean', zero_infinity=False)[source] The Connectionist Temporal Classification loss. Calculates loss between a continuous (unsegmented) time series and a target sequence. CTCLoss sums over the probability odocs.pytorch.org일단 ..

조금은 이제 알 것 같은....https://aclanthology.org/2025.acl-long.58/ ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion AttacksYu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.aclanthol..