전체 글271 [2025-1] 차승우 - Titans: Learning to Memorize at Test Time https://arxiv.org/abs/2501.00663 Titans: Learning to Memorize at Test TimeOver more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention allows attending toarxiv.org 0. Abstract 순환 모델은 데이터를 고정된 크기의 메모리(hidden state)로 압축하는 것을 .. 2025. 2. 17. [2025-1] 주서영 - Adding Conditional Control to Text-to-Image Diffusion Models ControlNetGitHub GitHub - lllyasviel/ControlNet: Let us control diffusion models!Let us control diffusion models! Contribute to lllyasviel/ControlNet development by creating an account on GitHub.github.comICCV 20233626회 인용1. Introduction기존 Text-Image 모델(Stable Diffusion, DALL·E 2, MidJourney, etc.)은 이미지 생성은 뛰어났지만 프롬프트를 수정하며 원하는 결과를 얻기까지 반복 작업이 필요하고 Fine-tuning에서는 데이터셋과 훈련 비용 등에 문제가 있었음ControlNet.. 2025. 2. 15. [2025-1] 임수연 - Large scale distributed neural network training through online distillation | Relational knowledge distillation | Be your own teacher: Improve the performance of convolutional neural networks via self distillation https://arxiv.org/pdf/1904.05068https://arxiv.org/pdf/1804.03235https://arxiv.org/pdf/1905.08094안녕하세요, 이번 글에서는 Distillation의 변형된 기법들을 차례로 알아가보도록 하겠습니다. 핵심 아이디어 위주로 정리하였으므로 실험과 같은 자세한 내용은 논문을 참고해주시면 감사하겠습니다. Knowledge 관점 1. Introduction새로운 approach로 RKD(Relational Knowledge Distillation)과 loss 2가지 distance-wise & angle-wise distillation losses 를 제안. metric learning에서 student model이 outperform 할 .. 2025. 2. 15. [2025-1] 차승우 - Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling https://arxiv.org/abs/1412.3555 Empirical Evaluation of Gated Recurrent Neural Networks on Sequence ModelingIn this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gatedarxiv.org0. Abstract- tanh RNN과 비교하.. 2025. 2. 15. 이전 1 ··· 15 16 17 18 19 20 21 ··· 68 다음
