-
## About
At [^1][^2], we shared a few notes about time series anomaly detection, and forecasting/prediction. Other than using traditional statistics-based time series forecasting methods like [Holt…
amotl updated
6 months ago
-
# [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/abs/2103.00020)
## TL;DR
- 자연어와 이미지를 함께 pre-training한 뒤, downstream task에 zero-shot transfer할 수 있는 방법인 C…
-
I have a question whether the pre-trained UniTS training dataset contains the test dataset. If so, then the training process of time series prediction and time series completion is essentially a self-…
-
[From Visual Prompt Learning to Zero shot transfer ](https://arxiv.org/pdf/2303.05266.pdf)
[Learning to Prompt for Vision-Language Models](https://link.springer.com/article/10.1007/s11263-022-01653…
-
Instead of having a unified generation function as we have now, we might want to adjust our repo in the future in a direction such that users can pick different approaches like:
For Generation:
`Z…
-
### Question
我看这个SGLang的例子中的questions的形式类似于zero-shot，请问我要做上下文学习有没有合适的例子呢？也就是我先给模型在之前的对话中提供多张图片并且分别告诉他们图片的含义，之后再让他推理另外的图片。这个功能怎么实现呢？
I think the form of the questions in this SGLang example is simi…
-
Hi, I did some experiment on MIT-States.
From my understanding, this is basically a kind of zero shot learning, and it is branded as "unseen combination" recognition task by Red Wine paper.
I have a…
-
## タイトル: DINO-X：オープンワールドの物体検出と理解のための統合ビジョンモデル
## リンク: https://arxiv.org/abs/2411.14347
## 概要:
本論文では、IDEA Researchが開発した統合オブジェクト中心ビジョンモデルDINO-Xを紹介します。これは、現時点で最高のオープンワールド物体検出性能を達成しています。DINO-Xは、Ground…
-
# URL
- https://arxiv.org/pdf/2109.01652
# Affiliations
- Jason Wei, N/A
- Maarten Bosma, N/A
- Vincent Y. Zhao, N/A
- Kelvin Guu, N/A
- Adams Wei Yu, N/A
- Brian Lester, N/A
- Nan Du, N…
-
## What's few-shot/zero-shot HPO
Few-shot HPO is a both promising-performance and budget-friendly HPO solution. It is divided into two processes: offline processing and online processing. In offline…