공대생 도전 일지

Context Generation 후 Answer Generation! - Generate rather than Retrieve: Large Language Models are Strong Context Generators

https://arxiv.org/abs/2209.10063 Generate rather than Retrieve: Large Language Models are Strong Context GeneratorsKnowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first retrieves a handfularxiv.org 실험을 진행해달라고 하길래 일단..

https://arxiv.org/abs/2411.18203 Critic-V: VLM Critics Help Catch VLM Errors in Multimodal ReasoningVision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoning paths. To addrarxiv.orgVLM은 추론 과제에서 발전을 보였으나 Hallucinati..

보호되어 있는 글입니다.

2025.02.25 - [인공지능/논문 리뷰 or 진행] - GRIT 생성과 Embedding을 동시에 Generative Representational Instruction Tuning - 논문 리뷰 GRIT 생성과 Embedding을 동시에 Generative Representational Instruction Tuning - 논문 리뷰https://arxiv.org/abs/2402.09906 기존 모델들은 생성만 잘하거나, Embedding만 잘 진행하였습니다.그리하여 둘 다 잘 하도록 두개 다 학습을 진행한 GRIT이 등장합니다.생성과 Representation 모두 진행하여 학yoonschallenge.tistory.com https://arxiv.org/abs/2402.09906 Generat..

https://arxiv.org/abs/2406.12846 DrVideo: Document Retrieval Based Long Video UnderstandingMost of the existing methods for video understanding primarily focus on videos only lasting tens of seconds, with limited exploration of techniques for handling long videos. The increased number of frames in long videos poses two main challenges: difficultarxiv.org 요약 기존 영상 이해 모델은 짧은 영상에 최적화되어 긴 영상에서 핵심 정보..

https://arxiv.org/abs/2401.17167 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex ScenariosThe recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using tool..

https://arxiv.org/abs/2408.04392 Open-domain Implicit Format Control for Large Language Model GenerationControlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instarxiv.orgLLM이 다양한 사용자의 출력 형식 요구를 충족하지 ..

https://advanced.onlinelibrary.wiley.com/doi/10.1002/advs.202412775여기서도 Transformer 기반으로 멀티 오믹스(Multi-omics) 데이터를 활용하여 만성 질환을 조기 예측합니다. 혈액 검사 데이터는 클러스터링하고, Multi-omics 데이터는 Transformer 기반으로 모델 학습하네요 연구 목적혈액검사와 multi-omics 데이터를 통합하여 저비용 고정밀 만성질환 조기 예측 시스템 개발대상 데이터- 고산 거주자 160명: 혈액·소변 → 전사체, 단백질체, 대사체 수집- 일반 임상 환자 314만 명의 20년 혈액 검사 및 진단 정보모델명Omicsformer – Transformer 기반 multi-omics 통합 딥러닝 모델방법론 핵심..

https://arxiv.org/abs/2410.11910 Explainable AI Methods for Multi-Omics Analysis: A SurveyAdvancements in high-throughput technologies have led to a shift from traditional hypothesis-driven methodologies to data-driven approaches. Multi-omics refers to the integrative analysis of data derived from multiple 'omes', such as genomics, proteomics,arxiv.orgexplainable는 딱히 필요 없어서... 연구 배경- Multi-Omics..

어 음갑자기 하게 되어서...일단... https://mhealth.jmir.org/2021/5/e22591 Acute Exacerbation of a Chronic Obstructive Pulmonary Disease Prediction System Using Wearable Device Data, Machine Learning, anWith rapid progress of medicine, many treatments and medications have been developed, and relationships between lifestyle and disease have been elucidated. Precision medicine involves determining the best trea..