본문 바로가기

분류 전체보기

 (27)
[논문 리뷰] Self-Attentive Sequential Recommendation (SASRec, 2018) 논문 리뷰 / Recommender System / Sequential Recommendation / Self-Attention / Next-Item Recommendation / SASRechttps://arxiv.org/abs/1808.09781Wang-Cheng Kang, Julian McAuley · UC San Diego · IEEE ICDM 2018 Self-Attentive Sequential RecommendationSequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions ..
[논문 리뷰] Auto-Encoding Variational Bayes (VAE, 2013) 논문 리뷰 / Generative Model / Variational Inference / Latent Variable Model / VAEhttps://arxiv.org/abs/1312.6114Diederik P. Kingma, Max Welling · Machine Learning Group, Universiteit van Amsterdam Auto-Encoding Variational BayesHow can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions..
[논문 리뷰] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models (SmoothQuant, 2023) 논문 리뷰 / LLM / Post-Training Quantization / W8A8 / INT8 Inference / SmoothQuanthttps://arxiv.org/abs/2211.10438Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han · MIT / NVIDIA SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language ModelsLarge language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can ..
[논문 리뷰] Efficient Streaming Language Models with Attention Sinks (StreamingLLM, 2024) 논문 리뷰 / LLM / Streaming Inference / Attention Sink / KV Cachehttps://arxiv.org/abs/2309.17453Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis · MIT / Meta AI / CMU / NVIDIA Efficient Streaming Language Models with Attention SinksDeploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed bu..
[논문 리뷰] Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5, 2020) 논문 리뷰 / NLP / Transfer Learning / Text-to-Text / T5https://arxiv.org/abs/1910.10683Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu Exploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerTransfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream..
[논문 리뷰] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ViT, 2020) 논문 리뷰 / Computer Vision / Vision Transformer / Image Classification / Self-Attentionhttps://arxiv.org/abs/2010.11929Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby · Google Research, Brain Team An Image is Worth 16x16 Words: Transformers for ..
[논문 리뷰] You Only Look Once: Unified, Real-Time Object Detection (YOLO, 2016) 논문 리뷰 / Computer Vision / Object Detection / YOLO / Real-Time Detectionhttps://arxiv.org/abs/1506.02640Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi · University of Washington / Allen Institute for AI / Facebook AI Research You Only Look Once: Unified, Real-Time Object DetectionWe present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers..
[논문 리뷰] When Attention Sink Emerges in Language Models: An Empirical View (Attention Sink, 2025) 논문 리뷰 / LLM / Attention Sink / Transformer / Language Model Pre-traininghttps://arxiv.org/abs/2410.10781Xiangming Gu, Tianyu Pang, Chao Du, Qian Liu, Fengzhuo Zhang, Cunxiao Du, Ye Wang, Min Lin When Attention Sink Emerges in Language Models: An Empirical ViewLanguage Models (LMs) assign significant attention to the first token, even if it is not semantically important, which is known as attenti..

티스토리툴바