任雨山

Seventy3

Technology ZH ↓ 756 episodes

73播客，名字取材于Sheldon最喜欢的数字，内容由NotebookLM生成，每天跟随AI读AI业界论文。

Be sure to visit the podcast's website and support the creator: www.xiaoyuzhoufm.com

Author

任雨山

Episodes

加餐001-Were RNNs All We Needed? 06.10.2024 6:00

Seventy3: 用NotebookLM将论文生成播客，让大家跟着AI一起进步。今天的主题是： Were RNNs All We Needed? Main Theme: This research paper revisits traditional recurrent neural networks (RNNs) like LSTMs and GRUs, proposing simplified versions – minLSTM and minGRU – that address the scalability limitations of their predecessors while achieving comparable performance to modern sequence models. Key Ideas...

【第五期】Movie Gen 05.10.2024 8:49

Seventy3: 用NotebookML将论文生成播客，让大家跟着AI一起进步。今天的主题是： Movie Gen: A Cast of Media Foundation Models This briefing document reviews the key themes and findings presented in the research paper "movie-gen-research-paper.pdf", focusing on the development and capabilities of Meta's MovieGen AI system. MovieGen is a suite of AI models designed for high-quality video and audio genera...

【第四期】LSTM original解读 04.10.2024 11:57

Seventy3: 用NotebookML将论文生成播客，让大家跟着AI一起进步。今天的主题是： Long Short-Term Memory (LSTM) Source: Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. Main Theme: This paper introduces Long Short-Term Memory (LSTM), a novel recurrent neural network (RNN) architecture designed to address the vanishing gradient problem that plagues tr...

【第三期】LSTM解读 03.10.2024 16:02

Seventy3: 用NotebookML将论文生成播客，让大家跟着AI一起进步。今天的主题是： Long Short-Term Memory-Networks for Machine Reading Source: Cheng, J., Dong, L., & Lapata, M. (2016). Long short-term memory-networks for machine reading. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (pp. 2094-2103). Main Theme: This paper introduces the Long Short-Term Memory-N...

【第二期】Transformer: Attention is All you Need 02.10.2024 9:56

Seventy3: 用NotebookML将论文生成播客，让大家跟着AI一起进步。今天的主题是： Attention Is All You Need Source: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30. Main Theme: This paper introduces the Transformer, a novel neural network architecture for sequence t...

【第一期】NeRF解读 02.10.2024 12:05

Seventy3: 用NotebookML将论文生成播客，让大家跟着AI一起进步。今天的主题是： NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis - A Detailed Briefing This briefing document reviews the key themes and findings presented in the paper "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis" by Ben Mildenhall et al. Core Idea: The paper introduces NeRF, a novel appro...