CODE - AI Dynamics

3 different people have sent me this video in under 24hrs, so I watched it and can confirm this is a VERY clear, accessible and spot on practical technical explainer of LLMs… great 101… by the ever-awesome @karpathy – highly recommended

→ View original post on X — @mustafasuleyman

23 November 2023

Building Transformers: Concept and Implementation from Scratch

By

@miketamir

–

23 November 2023 21h01

Transformer: Concept and code from scratch https://
bit.ly/45YXobu #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @miketamir

23 November 2023

4 Open-Source GPT-4 Vision Alternatives: Qwen-VL and CogVLM

By

@datachaz

–

23 November 2023 20h36

Looking for open-source #GPT4 Vision alternatives? Here are 4 excellent options Qwen-VL
– Code: https://
github.com/QwenLM/Qwen-VL
– Paper: https://
arxiv.org/abs/2308.12966
– Demo: https://
colab.research.google.com/github/camendu
ru/Qwen-VL-Chat-colab/blob/main/Qwen_VL_Chat_colab.ipynb
… CogVLM
– Code: https://
github.com/THUDM/CogVLM
– Paper: https://
arxiv.org/abs/2311.03079
– Demo:

→ View original post on X — @datachaz

23 November 2023

Q-Learning Graph Networks for SAT Solver Branching Heuristics

By

@montreal_ai

–

23 November 2023 17h58

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver? Kurin et al.: https://
arxiv.org/abs/1909.11830 #DeepLearning #QLearning #ReinforcementLearning

→ View original post on X — @montreal_ai

23 November 2023

A* Search Without Expansions: Deep Q-Networks Heuristics

By

@montreal_ai

–

23 November 2023 17h38

A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks Agostinelli et al.: https://
arxiv.org/abs/2102.04518 #ArtificialIntelligence #DeepQNetworks #ReinforcementLearning

→ View original post on X — @montreal_ai

23 November 2023