Computer Vision News

computer vision - culture, news & data

[Computer Vision News @CVCND]

4th workshop onVision-based InduStrialInspectiON (VISION)
VISION’26 @ CVPR: Vision-Based Industrial Inspection Across Modalities (Surface, X-ray, 3D & More)

https://t.co/R70sZqOG8i

[Computer Vision News @CVCND]

Deepfake makers can now evade an unusual detection method | New Scientist https://t.co/jAf8K8XNNG

[Andrew Ng @AndrewYNg]

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with @OpenAI, and taught by @colintjarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively!

Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs.

I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively.

In detail, you’ll:
- Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model
- Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell
- Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost
- Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o
- Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later
- Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance

You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance.

I think you'll find this course enjoyable and valuable.

Please sign up for it here: https://t.co/0XIGzinyrx

[Computer Vision News @CVCND]

AI Pioneer Fei-Fei Li Has a Vision for Computer Vision - IEEE Spectrum ⁦@drfeifei⁩ https://t.co/bys6i741gX

[Computer Vision News @CVCND]

https://t.co/ddsVW7vDTj

[Computer Vision News @CVCND]

A ranked list of awesome machine learning Python libraries. This curated list contains 920 awesome open-source projects with a total of 4.7M stars grouped into 34 categories. All projects are ranked by a project-quality score. https://t.co/IPts3i4kO1

[Computer Vision News @CVCND]

10 Essential Python Libraries for Data Science in 2024 - KDnuggets https://t.co/0hDDscVqKG

[Computer Vision News @CVCND]

How to browse at https://t.co/tKW5BDcN3c ...

[Leland McInnes @leland_mcinnes]

An ArXiv data map you can browse yourself:

https://t.co/ulpNmynrRf

(an early demo; please be gentle; use shift to lasso-select; click on a point to open the paper)

[Computer Vision News @CVCND]

Image Analysisis using Phyton, Matlab and Fiji: https://t.co/4RIqcnXM9X

[Computer Vision News @CVCND]

YOLO11 by ultralytics is here! https://t.co/mNh9wYwCgF

[Computer Vision News @CVCND]

#ECCV2024: Papers with Code https://t.co/stMk1mO70q

[Computer Vision News @CVCND]

All you need is attention... and excel
:)

[Tom Yeh @ProfTomYeh]

Self-Attention by hand ✍️ Excel ~ I designed this exercise for students to practice the QKV math. I also created a medium and a large version to show how the attention matrix grows quadratically as the sequence gets longer. 👇Join the 'AI Math' community. Download xlsx.

[Computer Vision News @CVCND]

A collection of resources, encompassing a wide range of tools, documents, resources, applications, and use cases related to ChatGPT. https://t.co/KaWSH5xLWV

[Computer Vision News @CVCND]

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques. https://t.co/VKjtnDn8xM

[Computer Vision News @CVCND]

UNet 3+: a U-shape encoder-decoder architecture built upon the foundation of its predecessors, i.e., UNet and UNet++. It aims to capture both fine-grained details and coarse-grained semantics from full scales. https://t.co/rz8CKHK0rk

[Computer Vision News @CVCND]

How to Access OpenAI o1? - Analytics Vidhya https://t.co/hq04fS14Fz

[Computer Vision News @CVCND]

see paper: https://t.co/sU6n80Srve

[Computer Vision News @CVCND]

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image https://t.co/Rrc1xbcnFO

[Computer Vision News @CVCND]

more applications of LLMs!!!

[Sam Nastase @samnastase]

Happy to see this work led by @zaidzada_ now published in @NeuroCellPress! We use LLM embeddings to capture word-by-word linguistic content transmitted from the speaker's brain to the listener's brain in real-time, face-to-face conversations: https://t.co/nexZ7RirQi

[Computer Vision News @CVCND]

AI achieves silver-medal standard solving International Mathematical Olympiad problems - Google DeepMind https://t.co/LNeJunNHb2