[video][motivation]
While this channel supposed to be pure technical I read / listen / watch some other resources to get idea about life and choices. Some times we are not getting what we thought we could and get stressed out although we put some much into making things for the better.
I’d like to share one of the worth watching / listening videos
https://youtu.be/3iMc8uF46C0?si=suiCgH4lwmyRA60A
While this channel supposed to be pure technical I read / listen / watch some other resources to get idea about life and choices. Some times we are not getting what we thought we could and get stressed out although we put some much into making things for the better.
I’d like to share one of the worth watching / listening videos
https://youtu.be/3iMc8uF46C0?si=suiCgH4lwmyRA60A
YouTube
I'm 40. If You're In Your 20's or 30's, Watch This
📩 Subscribe to my weekly newsletter: https://simonalexanderong.com/shots-of-energy/
📚 Get the new paperback version of my bestselling book Energize: https://getenergizebook.com/
👥 JOIN the waitlist for my new online community coming soon here: https://…
📚 Get the new paperback version of my bestselling book Energize: https://getenergizebook.com/
👥 JOIN the waitlist for my new online community coming soon here: https://…
👍4❤1
[ai][paper]
“Enabling effective collaboration among LLMs is a crucial step toward developing autonomous systems capable of solving complex problems. Al- though LLMs are typically used as single-model generators, where humans critique and refine their outputs, the potential for jointly trained collaborative models remains largely unexplored. Despite promising results in multi-agent communication and debate settings, little progress has been made
in training models to work together on tasks. In this paper, we present a first step towards ’Multi-agent LLM training’ (MALT) on reasoning problems. Our approach employs a sequential multi-
agent setup with heterogeneous LLMs assigned specialized roles: a generator, verifier, and refinement model iteratively solving problems. We propose a trajectory-expansion-based synthetic
data generation process and a credit assignment strategy driven by joint outcome-based rewards.
This enables our post-training setup to utilize both positive and negative trajectories to autonomously improve each model’s specialized capabilities as part of a joint sequential system. We evaluate our approach on MATH, GSM8k, and CSQA, where
MALT using Llama 3.1 8B models achieves rela tive improvements of 14.14%, 7.12%, and 9.40% respectively over the same baseline model. This demonstrates an early advance in multi-agent cooperative capabilities for performance on mathematical and common sense reasoning questions. More generally, our work provides a concrete direction for research around multi-agent LLM
training approaches.”
https://arxiv.org/abs/2412.01928
“Enabling effective collaboration among LLMs is a crucial step toward developing autonomous systems capable of solving complex problems. Al- though LLMs are typically used as single-model generators, where humans critique and refine their outputs, the potential for jointly trained collaborative models remains largely unexplored. Despite promising results in multi-agent communication and debate settings, little progress has been made
in training models to work together on tasks. In this paper, we present a first step towards ’Multi-agent LLM training’ (MALT) on reasoning problems. Our approach employs a sequential multi-
agent setup with heterogeneous LLMs assigned specialized roles: a generator, verifier, and refinement model iteratively solving problems. We propose a trajectory-expansion-based synthetic
data generation process and a credit assignment strategy driven by joint outcome-based rewards.
This enables our post-training setup to utilize both positive and negative trajectories to autonomously improve each model’s specialized capabilities as part of a joint sequential system. We evaluate our approach on MATH, GSM8k, and CSQA, where
MALT using Llama 3.1 8B models achieves rela tive improvements of 14.14%, 7.12%, and 9.40% respectively over the same baseline model. This demonstrates an early advance in multi-agent cooperative capabilities for performance on mathematical and common sense reasoning questions. More generally, our work provides a concrete direction for research around multi-agent LLM
training approaches.”
https://arxiv.org/abs/2412.01928
arXiv.org
MALT: Improving Reasoning with Multi-Agent LLM Training
Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in complex tasks. In this...
👍1
[book][Algorithms for Modern Hardware]
This is an upcoming high performance computing book noscriptd “Algorithms for Modern Hardware” by Sergey Slotin.
Its intended audience is everyone from performance engineers and practical algorithm researchers to undergraduate computer science students who have just finished an advanced algorithms course and want to learn more practical ways to speed up a program.
All book materials are hosted on GitHub, with code in a separate repository.
https://en.algorithmica.org/
This is an upcoming high performance computing book noscriptd “Algorithms for Modern Hardware” by Sergey Slotin.
Its intended audience is everyone from performance engineers and practical algorithm researchers to undergraduate computer science students who have just finished an advanced algorithms course and want to learn more practical ways to speed up a program.
All book materials are hosted on GitHub, with code in a separate repository.
https://en.algorithmica.org/
🔥4
[system programming][baseline]
What every system programmer should know in 12 pages:
https://assets.bitbashing.io/papers/concurrency-primer.pdf
What every system programmer should know in 12 pages:
https://assets.bitbashing.io/papers/concurrency-primer.pdf
🔥3
[paper][meta][large concept models]
“The current established technology of LLMs is to process input and generate output at the token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a “concept”. Concepts are language- and modality-agnostic and represent a higher level idea or action in a flow”
https://scontent-ams4-1.xx.fbcdn.net/v/t39.2365-6/470149925_936340665123313_5359535905316748287_n.pdf?_nc_cat=103&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=_Kelt2jn-pkQ7kNvgFRhMPH&_nc_zt=14&_nc_ht=scontent-ams4-1.xx&_nc_gid=AsqaBwO9TftbIqsIF6KCPA3&oh=00_AYAAj36Wbvgp4TU0V0JPoyHGs-_FesxPYaEwDvdGZcbtNw&oe=676768D2
github: https://github.com/facebookresearch/large_concept_model
“The current established technology of LLMs is to process input and generate output at the token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a “concept”. Concepts are language- and modality-agnostic and represent a higher level idea or action in a flow”
https://scontent-ams4-1.xx.fbcdn.net/v/t39.2365-6/470149925_936340665123313_5359535905316748287_n.pdf?_nc_cat=103&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=_Kelt2jn-pkQ7kNvgFRhMPH&_nc_zt=14&_nc_ht=scontent-ams4-1.xx&_nc_gid=AsqaBwO9TftbIqsIF6KCPA3&oh=00_AYAAj36Wbvgp4TU0V0JPoyHGs-_FesxPYaEwDvdGZcbtNw&oe=676768D2
github: https://github.com/facebookresearch/large_concept_model
[ai][genesis]
Amazing step toward with generating models. You can find multiple videos in the link:
https://genesis-embodied-ai.github.io/
Amazing step toward with generating models. You can find multiple videos in the link:
https://genesis-embodied-ai.github.io/
👍1
[ai][llm]
Large scale multimodal agents society
“In this paper, taking e-commerce
scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs.
In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents’ multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents’ behavior show that these agents achieve comparable performance to humans in behavioral indicators. “
https://arxiv.org/pdf/2412.09237
Large scale multimodal agents society
“In this paper, taking e-commerce
scenarios as an example, we present LMAgent, a very large-scale and multimodal agents society based on multimodal LLMs.
In LMAgent, besides freely chatting with friends, the agents can autonomously browse, purchase, and review products, even perform live streaming e-commerce. To simulate this complex system, we introduce a self-consistency prompting mechanism to augment agents’ multimodal capabilities, resulting in significantly improved decision-making performance over the existing multi-agent system. Moreover, we propose a fast memory mechanism combined with the small-world model to enhance system efficiency, which supports more than 10,000 agent simulations in a society. Experiments on agents’ behavior show that these agents achieve comparable performance to humans in behavioral indicators. “
https://arxiv.org/pdf/2412.09237
🌟 Happy New Year, everyone! 🌟
This year has been incredible, and I’m so grateful for each of you—our channel grew to 500+ amazing members! 🎉 Thank you for your support, engagement, and encouragement along the way.
I hope the articles, videos, and books shared here added value to your journey. Let’s make this new year even more inspiring and impactful together. Here’s to learning, growing, and achieving great things in 2024!
Cheers to a fantastic year ahead! 🥂✨Love you all 💛
This year has been incredible, and I’m so grateful for each of you—our channel grew to 500+ amazing members! 🎉 Thank you for your support, engagement, and encouragement along the way.
I hope the articles, videos, and books shared here added value to your journey. Let’s make this new year even more inspiring and impactful together. Here’s to learning, growing, and achieving great things in 2024!
Cheers to a fantastic year ahead! 🥂✨Love you all 💛
❤15🎉4
[neural networks]
A great video with building nerual network from scratch
https://www.youtube.com/watch?v=w8yWXqWQYmU
A great video with building nerual network from scratch
https://www.youtube.com/watch?v=w8yWXqWQYmU
YouTube
Building a neural network FROM SCRATCH (no Tensorflow/Pytorch, just numpy & math)
Kaggle notebook with all the code: https://www.kaggle.com/wwsalmon/simple-mnist-nn-from-scratch-numpy-no-tf-keras
Blog article with more/clearer math explanation: https://www.samsonzhang.com/2020/11/24/understanding-the-math-behind-neural-networks-by-building…
Blog article with more/clearer math explanation: https://www.samsonzhang.com/2020/11/24/understanding-the-math-behind-neural-networks-by-building…
👍1
[ai][agents]
https://huyenchip.com//2025/01/07/agents.html
https://huyenchip.com//2025/01/07/agents.html
Chip Huyen
Agents
Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines the field of AI research as “the study and design of rational…
[ai][deepseek][paper]
https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf
Model Summary
Architecture: Innovative Load Balancing Strategy and Training Objective
On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the performance degradation that arises from encouraging load balancing.
We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance. It can also be used for speculative decoding for inference acceleration.
Pre-Training: Towards Ultimate Training Efficiency
We design an FP8 mixed precision training framework and, for the first time, validate the feasibility and effectiveness of FP8 training on an extremely large-scale model.
Through co-design of algorithms, frameworks, and hardware, we overcome the communication bottleneck in cross-node MoE training, nearly achieving full computation-communication overlap. This significantly enhances our training efficiency and reduces the training costs, enabling us to further scale up the model size without additional overhead.
At an economical cost of only 2.664M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8T tokens, producing the currently strongest open-source base model. The subsequent training stages after pre-training require only 0.1M GPU hours.
https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf
Model Summary
Architecture: Innovative Load Balancing Strategy and Training Objective
On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the performance degradation that arises from encouraging load balancing.
We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance. It can also be used for speculative decoding for inference acceleration.
Pre-Training: Towards Ultimate Training Efficiency
We design an FP8 mixed precision training framework and, for the first time, validate the feasibility and effectiveness of FP8 training on an extremely large-scale model.
Through co-design of algorithms, frameworks, and hardware, we overcome the communication bottleneck in cross-node MoE training, nearly achieving full computation-communication overlap. This significantly enhances our training efficiency and reduces the training costs, enabling us to further scale up the model size without additional overhead.
At an economical cost of only 2.664M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8T tokens, producing the currently strongest open-source base model. The subsequent training stages after pre-training require only 0.1M GPU hours.
[llm] Super denoscriptive video from Andrej Karpathy
https://www.youtube.com/watch?v=7xTGNNLPyMI
https://www.youtube.com/watch?v=7xTGNNLPyMI
YouTube
Deep Dive into LLMs like ChatGPT
This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology"…
[cs][memory allocator][from scratch]
https://arjunsreedharan.org/post/148675821737/memory-allocators-101-write-a-simple-memory
https://arjunsreedharan.org/post/148675821737/memory-allocators-101-write-a-simple-memory
Tumblr
Memory Allocators 101 - Write a simple memory allocator
Code related to this article: github.com/arjun024/memalloc
This article is about writing a simple memory allocator in C.
We will implement malloc(), calloc(), realloc() and free().
This is a beginner...
This article is about writing a simple memory allocator in C.
We will implement malloc(), calloc(), realloc() and free().
This is a beginner...
👍1