From 76920bd450ab0e07d5163374ff93537bb4327b0e Mon Sep 17 00:00:00 2001 From: Patrick Liu Date: Fri, 29 Nov 2024 23:28:44 +0800 Subject: [PATCH] Add Oppotunities of FM --- README.md | 5 ++++- paper_notes/_template.md | 2 +- .../opportunities_foundation_models.md | 21 +++++++++++++++++++ 3 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 paper_notes/opportunities_foundation_models.md diff --git a/README.md b/README.md index 4814bcb..667e523 100755 --- a/README.md +++ b/README.md @@ -34,6 +34,9 @@ I regularly update [my blog in Toward Data Science](https://medium.com/@patrickl - [Multimodal Regression](https://towardsdatascience.com/anchors-and-multi-bin-loss-for-multi-modal-target-regression-647ea1974617) - [Paper Reading in 2019](https://towardsdatascience.com/the-200-deep-learning-papers-i-read-in-2019-7fb7034f05f7?source=friends_link&sk=7628c5be39f876b2c05e43c13d0b48a3) +## 2024-11 (1) +- [On the Opportunities and Risks of Foundation Models](https://arxiv.org/abs/2108.07258) [[Notes](paper_notes/opportunities_foundation_models.md)] + ## 2024-06 (8) - [LINGO-1: Exploring Natural Language for Autonomous Driving](https://wayve.ai/thinking/lingo-natural-language-autonomous-driving/) [[Notes](paper_notes/lingo_1.md)] [Wayve, open-loop world model] - [LINGO-2: Driving with Natural Language](https://wayve.ai/thinking/lingo-2-driving-with-language/) [[Notes](paper_notes/lingo_2.md)] [Wayve, closed-loop world model] @@ -199,7 +202,7 @@ I regularly update [my blog in Toward Data Science](https://medium.com/@patrickl ## 2023-04 (1) -- [UniAD: Planning-oriented Autonomous Driving](https://arxiv.org/abs/2212.10156) [[Notes](paper_notes/uniad.md)] [BEV, e2e, Hongyang Li] +- [UniAD: Planning-oriented Autonomous Driving](https://arxiv.org/abs/2212.10156) [[Notes](paper_notes/uniad.md)] CVPR 2023 best paper [BEV, e2e, Hongyang Li] diff --git a/paper_notes/_template.md b/paper_notes/_template.md index 2b30143..d3fa522 100644 --- a/paper_notes/_template.md +++ b/paper_notes/_template.md @@ -1,6 +1,6 @@ # [Paper Title](link_to_paper) -_June 2024_ +_November 2024_ tl;dr: Summarize the the main idea of the paper with one sentence. diff --git a/paper_notes/opportunities_foundation_models.md b/paper_notes/opportunities_foundation_models.md new file mode 100644 index 0000000..16e50f9 --- /dev/null +++ b/paper_notes/opportunities_foundation_models.md @@ -0,0 +1,21 @@ +# [On the Opportunities and Risks of Foundation Models](https://arxiv.org/abs/2108.07258) + +_November 2024_ + +tl;dr: Nice def and summary of FM. + +#### Overall impression +* A foundation model is any model that is trained on broad data (generally using self-supervision at scale) that can be adapted (e.g., fine-tuned) to a wide range of downstream tasks +* The significance of foundation models can be summarized by two words: **emergence** and **homogenization**. + * Emergence means that the behavior of a system is implicitly induced rather than explicitly constructed; + * Homogenization indicates the consolidation of methodologies for building machine learning systems across a wide range of applications + + + +#### Key ideas + + +#### Technical details + +#### Notes +