밤에 쓰는 편지 밤에 쓰는 편지

https://arxiv.org/pdf/1912.08517AbstractGlobal Autoregressive Models (GAMs) are a recent proposal [15] for exploiting global properties of sequences for data-efficient learning of seq2seq models. In the first phase of training, an Energy-Based model (EBM) [10] over sequences is derived. This EBM has high representational power, but is unnormalized and cannot be directly exploited for sampling. T..

https://arxiv.org/pdf/2012.11635https://github.com/naver/gdcMay 2021 (ICLR 2021)AbstractWe propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both “pointwise” and “distributional” constraints over the target LM — to our knowledge, the first model with such generality —..

https://arxiv.org/pdf/2210.03117https://github.com/muzairkhattak/multimodal-prompt-learning(CVPR 2023)Abstract Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Proc..

https://arxiv.org/pdf/2111.12853v3https://github.com/shogi880/DPLCLIP?tab=readme-ov-fileAbstract Domain generalization (DG) is a difficult transfer learning problem aiming to learn a generalizable model for unseen domains. Recent foundation models (FMs) are robust to many distribution shifts and, therefore, should substantially improve the performance of DG. In this work, we study generic ways t..

https://arxiv.org/pdf/2007.01434https://github.com/facebookresearch/DomainBed?tab=readme-ov-file어떻게 실험 setting을 해서 domain generalization ability를 증명할 것인가. 평소에 뭔가 개운하지 않았던, 간과하였던 부분. model 간의 performance 차이가 정말로 model의 generalization capability에 기인하는 것인지, 아니면 hyperparameter search 혹은 다른 실험적 요소에 의한 차이인지 명확하게 구분할 수가 없어서 답답했던 부분. 이게 정말 fair comparison인가. 어디다가 어떻게 비교를 해야 기존 대비 성능이 향상되었다고 말할 수 있는가.  어..

3개의 논문에서 제시하는 모델은 각각 다른 쓰임새와 독특한 특징을 보여주지만기저에 관통하는 공통된 concept이 있어서 흥미롭다."Reusing early layers" early layer의 feature representation을 leveraging함으로써 efficiency & performance improvement를 추구한다.  내가 동경하는 이상적 논문 형태"simple but effective!"1. Efficient Transfer Learning driven by Layer-wise Features Aggregationhttps://openreview.net/pdf?id=Q0tfRYadhchttps://github.com/MLAI-Yonsei/LFA* MotivationTransfe..

https://rbcborealis.com/research-blogs/a-high-level-overview-of-large-language-models/Jul, 12, 2023Since 2022, a series of AI systems have been introduced that enable machines to read, analyze, interpret, and derive meaning from human language. One such system is ChatGPT, which gained a over a hundred million users within a mere two months of its launch in November 2022. Its successor, GPT-4 was..

https://arxiv.org/pdf/2405.172474. Approaches for Responsible VLM EvaluationAs the main ability of VLMs is to map text with images, it is crucial to measure visio-linguistic abilities so as to ensure that the words are actually mapping to visual clues. Early tasks used to evaluate VLMs were image captioning and Visual Question Answering (VQA) [Antol et al., 2015]. In this section, we also discus..