26 Dec 2024, 12:24 UTC≈5,660 views6 reactionsread 8 August 2026 "Agents are not enough." New Microsoft research explores that for the latest wave of agents, differentiated by GenAI, to succeed, they need to work together with Sims and Assistants (see diagram on page 3):
Agents are nothing new, evolving from early agents (1950s) to expert systems (1980s), reactive agents (1990s), and more recently multi-agent systems and cognitive architectures.
While frameworks like AutoGen hel…
❤3👍3
Signed Artificial Intelligence
12 Oct 2024, 05:21 UTC≈9,500 views7 reactionsread 8 August 2026 Photo
Uber used RAG and AI agents to build its in-house Text-to-SQL, saving 140,000 hours annually in query writing time. 📈
Here’s how they built the system end-to-end:
The system is called QueryGPT and is built on top of multiple agents each handling a part of the pipeline.
1. First, the Intent Agent interprets user intent and figures out the domain workspace which is relevant to answer the question (e.g., Mobility, Bil…
👍5❤2
Signed Artificial Intelligence
6 Oct 2024, 02:50 UTC≈4,650 views9 reactionsread 8 August 2026 How Much GPU Memory Needed To Server A LLM ?
This is a common question that consistnetly comes up in interview or during the disscusiion with your business stakeholders.
And it’s not just a random question — it’s a key indicator of how well you understand the deployment and scalability of these powerful models in production.
As a data scientist understanding and estimating the require GPU memory is essential.
LLM…
👍6❤3
Signed Artificial Intelligence
30 Sept 2024, 14:13 UTC≈3,990 views1 reactionsread 8 August 2026 Best article on GenAI getting started
https://blog.bytebytego.com/p/where-to-get-started-with-genai
❤1
Signed Artificial Intelligence
29 Jul 2024, 12:29 UTC≈5,050 views5 reactionsread 8 August 2026 Photo
The matrix calculus for Deep Learning. Very well written. https://explained.ai/matrix-calculus/
👍5
Signed Artificial Intelligence
28 Jun 2024, 05:03 UTC≈5,500 views2 reactionsread 8 August 2026 Photo
Early result of Gemma 2 on the leaderboard, matching Llama-3-70B.
- Full data at leaderboard.lmsys.org
- Chat with Gemma 2 at chat.lmsys.org
- Gemma 2 blog goo.gle/3RLQXUa
🔥2
Signed Artificial Intelligence
9 May 2024, 13:51 UTC≈5,760 views7 reactionsread 8 August 2026 Forwarded from @Artificial_intelligence_in
Ai / Computer Vision Bootcamp🚀
Learn Ai / Computer Vision from Basics to Deployment from IITian and COEPian.
✅ Build Face Recognition ☺️
✅ Build Ai Object detection 🏍️🚇✈️
✅ Building Social Distancing App
✅ Build Automated Invoice reader 📃
✅Image Classification 🍘🥗
✅ Build Application of Computer Vision in Healthcare, Automotive, retail, Manufacturing and Security, Surveillance. 📸
+40 Hrs sessions.
+12 Weeks.
+13 To…
👍7
Signed Artificial Intelligence
23 Apr 2024, 16:41 UTC≈36,700 views6 reactionsread 8 August 2026 Photo
Microsoft just casually shared their new Phi-3 LLMs less than a week after Llama 3 release. Based on the benchmarks in technical report (https://arxiv.org/abs/2404.14219), even the smallest Phi-3 model beats Llama 3 8B despite being less than half the size.
Phi-3 has "only" been trained on 5x fewer tokens than Llama 3 (3.3 trillion instead of 15 trillion)
Phi-3-mini less has "only" 3.8 billion parameters, less than…
❤4👍2
Signed Artificial Intelligence
12 Apr 2024, 05:50 UTC≈5,160 views4 reactionsread 8 August 2026 Photo
Seems like GPT-4 is back on top with their latest update. Will have to wait and see how it compares in real time tests.
👍4
Signed Artificial Intelligence
11 Jan 2024, 15:53 UTC≈14,100 views5 reactionsread 8 August 2026 Good material on Developing AI systems in Medical Imaging: https://aiformedicalimaging.blogspot.com/2023/09/things-to-consider-when-developing-ai.html
👍5
Signed Artificial Intelligence
1 Jan 2024, 13:57 UTC≈7,910 views8 reactionsread 8 August 2026 Retrieval-Augmented Generation for Large Language Models: A survey
This paper is a must read.
It covers everything you need to know about the RAG framework and its limitations. It also lists different state-of-the-art techniques to boost its performance in retrieval, augmentation, and generation.
The ultimate goal behind these techniques is to make this framework ready for scalability and production use, especiall…
❤4👍4
Signed Artificial Intelligence
21 Dec 2023, 02:13 UTC≈5,950 views8 reactionsread 8 August 2026 Photo
Think of an LLM that can find entities in a given image, describe the image and answers questions about it, without hallucinating ✨
Kosmos-2 released by Microsoft is a very underrated model that can do that. ☃️ Not only this, but Hugging Face transformers integration makes it super easy to use!
Colab link:
https://colab.research.google.com/drive/1t25qM_lOM-HQG6Wg3aRiF4LOuQMN5lUF?usp=sharing
❤5🔥2👍1
Signed Artificial Intelligence
Showing the 12 most recent of 20 posts we hold for @awesomedeeplearning. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
