iiinova — where your digital self keeps evolving

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

"Densing Law of LLMs" paper: arxiv.org/abs/2412.04315

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

• The amount of work an LLM can handle on the same hardware is growing even faster than the improvements in model density or chip power alone. That's why researchers suggest focusing on improving "density" instead of just aiming for bigger and more powerful models.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Here are the key findings from the study: • Costs to run models are dropping as they are becoming more efficient. • The release of ChatGPT sped up the growth of efficiency of new models up to 50%! • Techniques like pruning and distillation don’t necessarily make models more efficient.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Estimating of effective parameter size: It combines a two-step process: - Loss Estimation: Links a model's size and training data to its accuracy - Performance Estimation: Uses a sigmoid function to predict how well a model performs based on its loss.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Scaling law: The density of a model is the ratio of its effective parameter size to its actual parameter size. If the effective size is close to or smaller than the actual size, the model is very efficient.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Why is density important? A higher-density model can deliver better results without needing more resources, reducing computational costs, making models suitable for devices with limited resources, like smartphones and avoiding unnecessary energy use.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Interestingly, they found a trend, called Densing Law: The capacity density of LLMs is doubling every 3 months, meaning that newer models are getting much better at balancing performance and size. Let's look at this more precisely:

100

Ksenia Se / Turing Post @turingpost.bsky.social · 11/12/2024

Reading about scaling laws recently I came by the interesting point: Focus on a balance between models' size and performance is more important that aiming for larger models Tsinghua University and ModelBest Inc propose the idea of “capacity density” to measure how efficiently a model uses its size

124

Ksenia Se / Turing Post @turingpost.bsky.social · 10/12/2024

2. AI system from World Labs, co-founded by Fei-Fei Li: Transforms a single image into interactive 3D scenes with varied art styles and realistic physics. You can explore, interact with elements and move within AI-generated environments directly in your web browser www.youtube.com/watch?v=lPYJ...

youtube.com

World Labs Unveils AI System That Transforms Single Images into Interactive 3D Worlds

YouTube video by Maginative

110

Ksenia Se / Turing Post @turingpost.bsky.social · 10/12/2024

1. GoogleDeepMind's Genie 2 Generates 3D environments with object interactions, animations, and physical effects from one image or text prompt. You can interact with them in real-time using a keyboard and mouse. Paper: deepmind.google/discover/blo... Our example: www.youtube.com/watch?v=YjO6...

100

Ksenia Se / Turing Post @turingpost.bsky.social · 10/12/2024

An incredible shift is happening in spatial intelligence! Here are 2 latest revolutional World Models, which create interactive 3D environments: 1. GoogleDeepMind's Genie 2 2. AI system from World Labs, co-founded by Fei-Fei Li Explore more below 👇

120

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

In our new AI 101 episode we discuss: - FM concepts for optimizing the path from noise to realistic data - Continuous Normalizing Flows (CNFs) - Conditional Flow Matching - Difference of FM and diffusion models Find out more: turingpost.com/p/flowmatching

turingpost.com

Topic 20: What is Flow Matching?

Explore the key concepts of Flow Matching, its relation to diffusion models, and how it can enhance the training of generative models

000

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

What is Flow Matching? Flow Matching (FM) is used in top generative models, like Flux, F5-TTS, E2-TTS, and MovieGen with state-pf-the-art results. Some experts even say that FM might surpass diffusion models👇

100

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

INTELLECT-1 by Prime Intellect INTELLECT-1 is a 10B open-source LLM trained over 42 days on 1T tokens across 14 global nodes, leverages the PRIME framework for exceptional efficiency (400× bandwidth reduction). github.com/PrimeIntelle...

100

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

MultiFoley by Adobe Research MultiFoley is an AI model generating high-quality sound effects from text, audio, and video inputs. Cool demos highlight its creative potential. arxiv.org/abs/2411.17698

100

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

ShowUI by Show Lab, NUS, Microsoft ShowUI is a 2B vision-language-action model tailored for GUI tasks: - features UI-guided token selection (33% fewer tokens) - interleaved streaming for multi-turn tasks - 256K dataset - achieves 75.1% zero-shot grounding accuracy arxiv.org/abs/2411.17465

100

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

OLMo 2 by Allen AI OLMo 2, a family of fully open LMs with 7B and 13B parameter, is trained on 5 trillion tokens. allenai.org/blog/olmo2

110

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

Alibaba’s QwQ-32B It excites with strong math, coding, and reasoning scores, ranking between Claude 3.5 Sonnet and OpenAI’s o1-mini. - Optimized for consumer GPUs through quantization - Open-sourced under Apache, revealing tokens and weights huggingface.co/Qwen/QwQ-32B...

huggingface.co

Qwen/QwQ-32B-Preview · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

110

Ksenia Se / Turing Post @turingpost.bsky.social · 05/12/2024

Amazing models of the week: • Alibaba’s QwQ-32B • OLMo 2 by Allen AI • ShowUI by Show Lab, NUS, Microsoft • Adobe's MultiFoley • INTELLECT-1 by Prime Intellect 🧵

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

Boundless Socratic Learning with Language Games, Google DeepMind This framework leverages recursive language-based "games" for self-improvement, focusing of feedback, coverage, and scalability. It suggests a roadmap for scalable AI via autonomous data gen and feedback loops arxiv.org/abs/2411.16905

110

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

MH-MoE: Multi-Head Mixture-of-Experts @msftresearch.bsky.social’s MH-MoE improves sparse MoE by adding multi-head attention, reducing perplexity without increasing FLOPs, and demonstrating robust performance under quantization. arxiv.org/abs/2411.16205

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

LLM-as-a-Judge: Presents a taxonomy of methodologies and applications of LLMs for judgment tasks, highlighting bias, vulnerabilities, and self-judgment, with future directions in human-LLM collaboration and bias mitigation arxiv.org/abs/2411.16594

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

Star Attention: NVIDIA introduced a block-sparse attention mechanism for Transformer-based LLMs. It uses local/global attention phases to achieve up to 11x inference speedup on sequences up to 1M tokens, retaining 95-100% accuracy. arxiv.org/abs/2411.17116 Code: github.com/NVIDIA/Star-...

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

Natural Language Reinforcement Learning: Redefines reinforcement learning components using natural language for interpretable and knowledge-rich decision-making. arxiv.org/pdf/2411.14251 t.co/Kru1Hz1JcX bsky.app/profile/turi...

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

Top 5 researches of the week: • Natural Language Reinforcement Learning • Star Attention, NVIDIA • Opportunities and Challenges of LLM-as-a-judge • MH-MoE: Multi-Head Mixture-of-Experts, @msftresearch.bsky.social • Boundless Socratic Learning with Language Games, Google DeepMind 🧵

120

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

I'm writing detailed overviews of AI agents and agentic workflows, and my latest article is about building agentic systems. If you're interested - take a look -> www.turingpost.com/p/aia5

turingpost.com

🦸🏻#5: Building Blocks of Agentic Systems

What powers an AI agent?

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

Paper: Large Language Model-Brained GUI Agents: A Survey arxiv.org/abs/2411.18279

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

By combining these components, LLM-brained GUI agents can adapt to different software, handling complicated workflows and following natural language commands.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

5. Memory and tracking progress: For tasks with multiple steps, the agent keeps track of what it has already done and what’s left to do. This memory helps it adjust if something unexpected happens. Agents can even store knowledge to improve over time or adapt to new tasks.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

4. Taking action: Based on the LLM’s plan, the agent carries out actions (clicking buttons, typing, or swiping) to directly interact with the app or software and completing each step of the task.

110

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

3. Model inference: Thinking and deciding The agent sends the prompt to the LLM, which is the "brain" of the system. The LLM processes the info and creates a plan of actions, like “Click this button, then type this text”. AI is often fine-tuned to improve GUIs' understanding.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

2. Prompt engineering or creating a plan: After "looking" at the screen, the agent prepares a prompt for the AI model, which includes the user’s instructions, the visual data (like screenshots or buttons layout), and other context the agent needs to understand the task.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

1. Understanding the environment: Firstly, the agent needs to "see" the software it’s working with. This is done through methods that capture the layout of the app or website, such as screenshots, lists of buttons and menus called widget trees.

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

This survey (which is really worth exploring!) dives deeper into: - How these agents evolved - Techniques and components to build them - Their challenges and potential Now, let’s take a closer look at how these agents work:

100

Ksenia Se / Turing Post @turingpost.bsky.social · 02/12/2024

LLM-brained GUI agents are a way to interact with GUIs in a much more flexible and human-like way. They blend LLMs' capabilities with software interaction to work with websites, mobile apps, and desktop software, simplifying complex tasks. A new survey on LLM-brained GUI agents was published👇

111

Ksenia Se / Turing Post @turingpost.bsky.social · 01/12/2024

Hope this helps! We also collected this list of Github Repositories in our Twitter Library. All in one place for your convenience -> www.turingpost.com/p/10-github-... If you found this useful, please like, comment, share and save this list! 🤍

turingpost.com

Top 10 GitHub Repositories to Master AI, Machine Learning and Data Science

000

Ksenia Se / Turing Post @turingpost.bsky.social · 01/12/2024

Our TuringPost Twitter Library provides useful resources, such as lists of tools and models, papers and courses on various popular aspects of AI and machine learning for you every week. Check it out. www.turingpost.com/t/Twitter-Li...

100

Ksenia Se / Turing Post @turingpost.bsky.social · 01/12/2024

4. Data Science Masters - 25.1k stars Concerned with "upper-level" college course material in math, programming, economics, and related disciplines. github.com/datasciencem...

github.com

GitHub - datasciencemasters/go: The Open Source Data Science Masters

The Open Source Data Science Masters. Contribute to datasciencemasters/go development by creating an account on GitHub.

100