datapture Reposted

LLMs are powerful but often struggle with causal reasoning and planning in environments. What if we could enhance their abilities by integrating causal representation learning? Introducing our new framework: Bridging LLMs and Causal World Models for reasoning and planning!


datapture Reposted

The amazing view of table tennis serves in slow motion [📹 vinogradovtt]


datapture Reposted

If you have a bad posture do this exercise 👇👇👇


datapture Reposted

Microsoft just changed the game! 🔥 They've open-sourced bitnet.cpp: a blazing-fast 1-bit LLM inference framework that runs directly on CPUs. Why is this a game-changer❓ You can now run 100B parameter models on local devices with up to 6x speed improvements and 82% less…


About 50% of managers surveyed by Beautiful.AI  said they believed artificial-intelligence tools could result in lower pay for managers, while 64% of managers said AI’s output and productivity was equal to the level of experienced managers bizjournals.com/bizwomen/news/…


datapture Reposted

We spent a year developing cde-small-v1, the best BERT-sized text embedding model in the world. today, we're releasing the model on HuggingFace, along with the paper on ArXiv. I think our release marks a paradigm shift for text retrieval. let me tell you why👇

Tweet Image 1

datapture Reposted

Two can't-miss online events next week; everyone's invited! All programming languages and experience levels are welcome. 1. Rust in Web3: Hacker Series ​​📅 Sept 24th ​​🕒 10 AM (PST) Join: lu.ma/hvw0n4ov 2. Web3 Tech Stacks: Deep Dives into Architecture and Design…


"IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control." arxiv.org/abs/2407.07061


datapture Reposted

🗞️ Paper - "A Note on LoRA" from Microsoft For deploying LoRA at scale. 📌 Describe one approach to enable serving multiple LoRA models at once, which can support requests pointing to multiple LoRA models, without swapping the LoRA weights, while maintaining latency comparable…

Tweet Image 1

datapture Reposted

do large-scale vision models represent the 3D structure of objects? excited to share our benchmark: multiview object consistency in humans and image models (MOCHI) with @xkungfu @YutongBAI1002 @thomaspocon @_yonifriedman @Nancy_Kanwisher Josh Tenenbaum and Alexei Efros 1/👀

Tweet Image 1

datapture Reposted

Probability Cheat Sheet:

Tweet Image 1

datapture Reposted

During my #MachineLearning course, a student approached me after a lecture on Principal Component Analysis (PCA) with insightful questions: "What do the component loadings look like?" and "How do they behave?" Motivated by this curiosity, I went back to my office and developed…


datapture Reposted

New course with @Intel! Multimodal RAG: Chat with Videos is available starting today! Learn from @Vasudev_Lal to build an AI chat system that answers questions from video content! Learn to: 🔄 Create embeddings from videos 🧩 Build a RAG pipeline for data retrieval 💬 Use…


datapture Reposted

Attention is awesome! So we (@NeuroLei @arisbenjamin @ml_tuberlin @KordingLab and #NeuroAi) built a biologically inspired model of visual attention and binding that can simultaneously learn and perform multiple attention tasks 🧠 Pre-print: doi.org/10.1101/2024.0… A 🧵...


datapture Reposted

Build your own RAG-based document QA system with Kotaemon, an open-source UI for chatting with your documents 📚🤖 Learn how to: ➡️ Set up a clean, customizable RAG UI for end users and developers ➡️ Organize LLM & embedding models, supporting both local and API providers ➡️…

Tweet Image 1

datapture Reposted

Si Milei dice haber devuelto 15 puntos del PBI al sector privado, ¿por qué seguimos en recesión? Si esos recursos están en el mercado ahora, ¿dónde está la inversión y el crecimiento? La economía sigue estancada.

Mi nota de hoy en @infobae ¿Cómo se explica la recesión si el Gobierno le devolvió al sector privado 15 puntos del PBI? - Infobae infobae.com/opinion/2024/0…



datapture Reposted

NASA's "Introduction to Tensors": grc.nasa.gov/www/k-12/Numbe…

Tweet Image 1

datapture Reposted

Microsoft's Self-play muTuAl Reasoning (rStar) code is available on Github now.

Tweet Image 1

"Mutual Reasoning" improves GSM8K accuracy from 13% to 64% - @Microsoft research. 📌 rStar boosts small language models's (SLMs) reasoning capabilities without fine-tuning or superior models through self-play mutual reasoning. Decouples reasoning into generation-discrimination…

Tweet Image 1


datapture Reposted

FREE Fourier Transform ebook, 2024. Download pdf from: jamesstone.sites.sheffield.ac.uk/books

Tweet Image 1

datapture Reposted

C programming + matrix multiplication creating LLM’s by hand!

From Tom Yeh

United States Trends
Loading...

Something went wrong.


Something went wrong.