Machine Learning - Revision history

Dvernon at 15:49, 20 August 2026

2026-08-20T15:49:37Z

Dvernon at 15:49, 20 August 2026

2026-08-20T15:49:19Z

Dvernon at 15:49, 20 August 2026

2026-08-20T15:49:07Z

Dvernon: /* Foundation Models: Large Language Models & Multimodal Models */

2026-08-20T15:45:50Z

‎Foundation Models: Large Language Models & Multimodal Models

Dvernon: /* Foundation Models: Large Language Models & Multimodal Models */

2026-08-20T15:44:54Z

‎Foundation Models: Large Language Models & Multimodal Models

Dvernon at 15:43, 20 August 2026

2026-08-20T15:43:08Z

Dvernon at 15:41, 20 August 2026

2026-08-20T15:41:16Z

Dvernon: Created page with "(Also see Artificial Intelligence and Robotics) === Bayesian Approaches === [https://machinelearningmastery.com/introduction-to-bay..."

2026-08-20T13:28:04Z

Created page with "(Also see Artificial Intelligence and Robotics) === Bayesian Approaches === [https://machinelearningmastery.com/introduction-to-bay..."

New page

(Also see [[#Artificial_Intelligence|Artificial Intelligence]] and [[#Robotics|Robotics]])

=== Bayesian Approaches ===
[https://machinelearningmastery.com/introduction-to-bayesian-belief-networks/ A Gentle Introduction to Bayesian Belief Networks] 

=== Books and Resources ===
[https://acems.org.au/data-science-machine-learning-book-download Data Science and Machine Learning]; free book to download 
[http://www.deeplearningbook.org/ Deep Learning] by Ian Goodfellow, Yoshua Bengio, and Aaron Courville 
[https://huggingface.co/ Hugging Face] "The platform where the machine learning community collaborates on models, datasets, and applications" 
[http://www.mbmlbook.com/index.html Model-based Machine Learning], co-authored by Chris Bishop, and the related [https://dotnet.github.io/infer/ Infer.NET] framework running Bayesian inference in graphical models 
[https://www.microsoft.com/en-us/research/wp-content/uploads/2016/05/Bishop-MBML-2012.pdf Model-based Machine Learning Companion Paper], C. M. Bishop, Phil. Trans. R. Soc. A 2013 371: 20120222; see Section 4. for an overview of probabilistic graphical models. 
[https://www.pyimagesearch.com/deep-learning-computer-vision-python-book/ Deep Learning for Computer Vision with Python]; great book and software, including a fully-configured virtual machine. 

=== Comparisons ===
[https://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html Classifier Comparison] with instructive visualization 
[https://www.wired.com/video/watch/5-levels-machine-learning Computer Scientist Explains Machine Learning in 5 Levels of Difficulty] 
[https://www.asimovinstitute.org/neural-network-zoo/ Neural Network Zoo] from Fjodor van Veen, The Asimov Institute 
[https://www.asimovinstitute.org/neural-network-zoo-prequel-cells-layers/ Neural Network Zoo Prequel: Cells and Layers] with more detail on how each cell type works 

=== Datasets ===
[https://huggingface.co/ Hugging Face] "The platform where the machine learning community collaborates on models, datasets, and applications" 
[https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data Kaggle Facial Expression Recognition dataset FER13] 

=== Deep Learning ===
[https://machinelearningmastery.com/what-is-deep-learning/ Deep Learning] overview 
[http://neuralnetworksanddeeplearning.com/ Neural Networks and Deep Learning] 
[https://arxiv.org/pdf/1702.07800.pdf On the Origin of Deep Learning] Haohan Wang and Bhiksha Raj 
[http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf The original paper on the CNN] by Yann LeCun, Leon Bottio, Yoshua Bengio, and Patrick Haffner 

=== Environments ===
[https://colab.research.google.com/?utm_source=scs-index Colab] from Google 
[https://huggingface.co/ Hugging Face] "The platform where the machine learning community collaborates on models, datasets, and applications" 
[https://developer.ibm.com/tutorials/iot-deep-learning-anomaly-detection-5/ Using Keras and TensorFlow for Anomaly Detection] (including the use of LSTM) 

=== Ethical Issues ===
[https://www.theguardian.com/technology/2018/nov/12/deep-fakes-fake-news-truth Deep fakes: one element of the dark side of AI and ML] 
[https://www.theguardian.com/technology/ng-interactive/2019/jun/22/the-rise-of-the-deepfake-and-the-threat-to-democracy The rise of the deepfake and the threat to democracy] 
[https://www.gwern.net/Tanks The Tank Story] 

=== Gaussian Processes ===
[https://distill.pub/2019/visual-exploration-gaussian-processes/ Gaussian processes] - Visual exploration of Gaussian processes 
[http://www.infinitecuriosity.org/vizgp/ Gaussian processes] - Interactive Gaussian process visualization 
[http://gaussianprocess.org/gpml/ Gaussian processes] - Gaussian Processes for Machine Learning (Rasmussen and Williams, 2006) 
[https://www.cs.toronto.edu/~duvenaud/cookbook/ Gaussian processes] - The Kernel Cookbook: Advice on Covariance functions 
[https://towardsdatascience.com/an-intuitive-guide-to-gaussian-processes-ec2f0b45c71d Gaussian processes] - An intuitive guide to Gaussian processes 
[https://arxiv.org/pdf/2009.10862.pdf Gaussian processes] - An Intuitive Tutorial to Gaussian Processes Regression (Wang, 2022) 
[https://www.youtube.com/watch?v=4vGiHC35j9s Gaussian processes] - Introduction to Gaussian Processes Video Lecture (Nando de Freitas, 2013) 

=== Generative Adversarial Networks ===
[https://medium.com/@jonathan_hui/gan-gan-series-2d279f906e7b GAN Series]; comprehensive overview of Generative Adversarial Networks 

=== Foundation Models: Large Language Models & Multimodal Models ===
(Also see [[#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[#Limitations_of_AI|Limitations of AI]])

[[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; 
see also this insightful [https://www.theguardian.com/news/ng-interactive/2025/sep/16/song-chun-zhu-why-one-of-the-worlds-most-brilliant-ai-scientists-left-the-us-for-china article] about Song-Chun Zhu, the director of BIGAI, and his vision of the future of AI 
[https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 
[https://www.theguardian.com/commentisfree/2020/sep/08/robot-wrote-this-article-gpt-3 A robot wrote this entire article. Are you scared yet, human?] GPT-3 
[https://hai.stanford.edu/news/how-trustworthy-are-large-language-models-gpt How Trustworthy Are Large Language Models Like GPT?] Stanford University Human-Centered Artificial Intelligence 
[https://www.theguardian.com/technology/2023/oct/19/music-lawsuit-ai-song-lyrics-anthropic Music publishers sue Amazon-backed AI company over song lyrics] 
[https://www.theguardian.com/technology/2023/jul/10/sarah-silverman-sues-openai-meta-copyright-infringement Sarah Silverman sues OpenAI and Meta claiming AI training infringed copyright] 
[https://www.theguardian.com/technology/2022/jun/15/techscape-google-chatbot-lamda-sentient-artificial-intelligence TechScape: why you shouldn’t worry about sentient AI … yet] 
[https://www.theguardian.com/technology/2024/apr/18/meta-ai-llama3-release Meta steps up AI battle with OpenAI and Google with release of Llama 3] 
[https://openai.com/index/dall-e-3/ DALL·E 3] Generative AI image creation from OpenAI 
[https://www.3blue1brown.com/lessons/mini-llm Large Language Models explained briefly] by Grant Sanderson, [https://www.3blue1brown.com/ 3Blue1Brown] 
[https://stability.ai/news/stable-diffusion-3 Stable Diffusion] Generative AI image creation from Stability AI 
[https://updates.midjourney.com/version-6-1/ Midjourney] Generative AI image creation from from Midjourney Inc. 
[https://openai.com/index/gpt-4/ GPT-4] and [https://chatgpt.com/ ChatGPT] from OpenAI 
[https://ai.meta.com/blog/meta-llama-3-1/ Llama 3] from Meta 
[https://gemini.google.com/ Gemini] (formerly known as BARD) from Google 
[https://www.wired.com/story/lamda-sentient-ai-bias-google-blake-lemoine/ LaMDA and the Sentient AI Trap] 
[https://humane-ai.dice.aalto.fi/ Collaborative AI Arena] Benchmarking collaborative capabilities of AI in the wild 
[https://truereason.app/chat TrueReason AI Tutor Demo] 
[https://sloanreview.mit.edu/article/three-things-to-know-about-prompting-llms/ Three Things to Know About Prompting LLMs] 
[https://spectrum.ieee.org/prompt-engineering-is-dead AI Prompt Engineering is Dead] Long live AI prompt engineering (IEEE Spectrum) 
[https://www.lakera.ai/blog/what-is-in-context-learning What is In-context Learning, and how does it work: The Beginner’s Guide] 
[https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/ What Is Retrieval-Augmented Generation, aka RAG?] a blog by Nvidia; here is how [https://chat.langchain.com/ Chat LangChain] from [https://www.langchain.com/ LangChain] explains it using [https://chat.langchain.com/?threadId=4968c618-f1e0-4e81-8283-9ed861bf45aa Claude 3.5 Haiku], [https://chat.langchain.com/?threadId=efeffb11-a227-41fe-8d40-f5e21288a34b GPT4.1 Mini] and [https://chat.langchain.com/?threadId=fa410c08-9c35-4954-8b30-a2c961006c89 Gemini 2.0 Flash] 
[https://ai.meta.com/blog/adapting-large-language-models-llms/ Methods for adapting large language models] from Meta 
[https://molmo.allenai.org/ Molmo] Multimodal Open Language Model built by [https://allenai.org/ Ai2] 
[https://arxiv.org/abs/2108.07258 On the Opportunities and Risks of Foundation Models] arXiv article 
[[File:new.jpg]] [https://www.ibm.com/think/topics/mamba-model What is a Mamba model?] 

=== Physics Informed Machine Learning ===
[https://www.youtube.com/watch?v=JoFW2uSd3Uo High Level Overview of AI and ML in Science and Engineering] 

=== Recurrent Neural Networks ===
[https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21 Illustrated guide to LSTMs and GRUs: a step by step explanation] 
[https://developer.ibm.com/tutorials/iot-deep-learning-anomaly-detection-1/ Introducing Deep Learning and Long Short-Term Memory Networks] 
[https://www.bioinf.jku.at/publications/older/2604.pdf The original paper on the LSTM] by Sepp Hochreiter and Jurgen Schmidhuber 
[http://karpathy.github.io/2015/05/21/rnn-effectiveness/ The Unreasonable Effectiveness of Recurrent Neural Networks] a blog by Andrej Karpathy 
[https://karpathy.github.io/ Andrej Karpathy's Blog] 
[http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Understanding LSTMs] 

=== Reinforcement Learning ===
[https://lilianweng.github.io/posts/2018-02-19-rl-overview/ A (Long) Peek into Reinforcement Learning] 
[https://bair.berkeley.edu/blog/2017/09/12/learning-to-optimize-with-rl/ Learning to Optimize with Reinforcement Learning] and learning to learn 
[https://arxiv.org/abs/1606.01885 Learning to Optimize] 

=== Robot Learning ===

[https://www.i-aida.org/resources/robot-learning/ Robot Learning] a talk by Jan Peters 
[https://sites.google.com/view/hirl-education/home Human-Interactive Robot Learning] a course developed in [https://www.humane-ai.eu/project/tmp-038/ Micro Project TMP-038] as part of the [https://www.humane-ai.eu HumanE-AI-Net Network of Excellence] (click the Home text at the top-right of the page to access the slides) 

=== Self-Supervised Learning ===
[https://project.inria.fr/paiss/files/2018/07/zisserman-self-supervised.pdf Self-supervised Learning] Andrew Zisserman 
[https://medium.com/syncedreview/yann-lecun-cake-analogy-2-0-a361da560dae Yann LeCun Cake Analogy 2.0]; the slides from his ISCC talk are
[https://twitter.com/ylecun/status/1097532314614034433 here] and the video of the talk is [http://isscc.org/2019-videos/ here] 

=== Transformers ===
[https://proceedings.neurips.cc/paper_files/paper/2023/file/57a9b97477b67936298489e3c1417b0a-Paper-Conference.pdf Energy Transformer] NeurIPS 2023 (note: Energy Transformers are not the same as Energy-Based Transformers) 
[https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 (Note: Energy-Based Transformers are not the same as Energy Transformers) 
[https://www.ai4europe.eu/research/research-bundles/multimodal-perception-and-interaction-transformers Multimodal Perception and Interaction with Transformers] HumanE-AI-Net Micro Project 
[http://crowley-coutaz.fr/jlc/Courses/ACAI2021/Multimodal-Transformer-Tutorial.html Multimodal Perception and Interaction with Transformers] Tutorial Presented at ACAI 2021 
[http://crowley-coutaz.fr/jlc/HumanE-AI-Net/TransfomerMicroProject/TransformerTools.pdf Multimodal Perception and Interaction with Transformers] Research Tools 
[http://crowley-coutaz.fr/jlc/HumanE-AI-Net/TransfomerMicroProject/ReseachChallengesDataSets.pdf Multimodal Perception with Transformers] Research Challenges and Data Sets 
[https://jalammar.github.io/illustrated-transformer/ The Illustrated Transformer] by Jay Alammar

@@ Line 1: / Line 1: @@
-(Also see [[Artificial_Intelligence|Artificial Intelligence]] and [[Robotics|Robotics]])
+(Also see [[Artificial_Intelligence|Artificial Intelligence]] and [[Robotics|Robotics]])<BR>
-[[File:new.jpg]] signifies a recently added item <BR>
+[[File:new.jpg]] signifies a recently added item
 == Bayesian Approaches ==

@@ Line 1: / Line 1: @@
 (Also see [[Artificial_Intelligence|Artificial Intelligence]] and [[Robotics|Robotics]])
-[[File:new.jpg]] signifies a recently added item
+[[File:new.jpg]] signifies a recently added item <BR>
 == Bayesian Approaches ==

← Older revision		Revision as of 15:49, 20 August 2026
Line 1:		Line 1:
	(Also see [[Artificial_Intelligence\|Artificial Intelligence]] and [[Robotics\|Robotics]])		(Also see [[Artificial_Intelligence\|Artificial Intelligence]] and [[Robotics\|Robotics]])
		+	[[File:new.jpg]] signifies a recently added item

	== Bayesian Approaches ==		== Bayesian Approaches ==

@@ Line 51: / Line 51: @@
 == Foundation Models: Large Language Models & Multimodal Models ==
-(Also see [[Robotics#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[Artificial_Intelligence#Limitations_of_AI|Limitations of AI]])
+(Also see [[Robotics#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[Artificial_Intelligence#Limitations_of_Generative_AI|Limitations of Generative AI]])
 [[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)]] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; <BR>

@@ Line 51: / Line 51: @@
 == Foundation Models: Large Language Models & Multimodal Models ==
-(Also see [[#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[#Limitations_of_AI|Limitations of AI]])
+(Also see [[Robotics#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[Artificial_Intelligence#Limitations_of_AI|Limitations of AI]])
-[[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; <BR>
+[[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)]] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; <BR>
 see also this insightful [https://www.theguardian.com/news/ng-interactive/2025/sep/16/song-chun-zhu-why-one-of-the-worlds-most-brilliant-ai-scientists-left-the-us-for-china article] about Song-Chun Zhu, the director of BIGAI, and his vision of the future of AI <BR>
 [https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 <BR>

← Older revision		Revision as of 15:43, 20 August 2026
Line 1:		Line 1:
−	(Also see [[#Artificial_Intelligence\|Artificial Intelligence]] and [[#Robotics\|Robotics]])	+	(Also see [[Artificial_Intelligence\|Artificial Intelligence]] and [[Robotics\|Robotics]])

	== Bayesian Approaches ==		== Bayesian Approaches ==

@@ Line 1: / Line 1: @@
 (Also see [[#Artificial_Intelligence|Artificial Intelligence]] and [[#Robotics|Robotics]])
-=== Bayesian Approaches ===
+== Bayesian Approaches ==
 [https://machinelearningmastery.com/introduction-to-bayesian-belief-networks/ A Gentle Introduction to Bayesian Belief Networks] <BR>
-=== Books and Resources ===
+== Books and Resources ==
 [https://acems.org.au/data-science-machine-learning-book-download Data Science and Machine Learning]; free book to download <BR>
 [http://www.deeplearningbook.org/ Deep Learning] by Ian Goodfellow, Yoshua Bengio, and Aaron Courville <BR>
@@ Line 12: / Line 12: @@
 [https://www.pyimagesearch.com/deep-learning-computer-vision-python-book/ Deep Learning for Computer Vision with Python]; great book and software, including a fully-configured virtual machine. <BR>
-=== Comparisons ===
+== Comparisons ==
 [https://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html Classifier Comparison] with instructive visualization <BR>
 [https://www.wired.com/video/watch/5-levels-machine-learning Computer Scientist Explains Machine Learning in 5 Levels of Difficulty] <BR>
@@ Line 18: / Line 18: @@
 [https://www.asimovinstitute.org/neural-network-zoo-prequel-cells-layers/ Neural Network Zoo Prequel: Cells and Layers] with more detail on how each cell type works <BR>
-=== Datasets ===
+== Datasets ==
 [https://huggingface.co/ Hugging Face] "The platform where the machine learning community collaborates on models, datasets, and applications" <BR>
 [https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data Kaggle Facial Expression Recognition dataset FER13] <BR>
-=== Deep Learning ===
+== Deep Learning ==
 [https://machinelearningmastery.com/what-is-deep-learning/ Deep Learning] overview <BR>
 [http://neuralnetworksanddeeplearning.com/ Neural Networks and Deep Learning] <BR>
@@ Line 28: / Line 28: @@
 [http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf The original paper on the CNN] by Yann LeCun, Leon Bottio,  Yoshua Bengio, and Patrick Haffner <BR>
-=== Environments ===
+== Environments ==
 [https://colab.research.google.com/?utm_source=scs-index Colab] from Google <BR>
 [https://huggingface.co/ Hugging Face] "The platform where the machine learning community collaborates on models, datasets, and applications" <BR>
 [https://developer.ibm.com/tutorials/iot-deep-learning-anomaly-detection-5/ Using Keras and TensorFlow for Anomaly Detection] (including the use of LSTM)<BR>
-=== Ethical Issues ===
+== Ethical Issues ==
 [https://www.theguardian.com/technology/2018/nov/12/deep-fakes-fake-news-truth Deep fakes: one element of the dark side of AI and ML] <BR>
 [https://www.theguardian.com/technology/ng-interactive/2019/jun/22/the-rise-of-the-deepfake-and-the-threat-to-democracy The rise of the deepfake and the threat to democracy]<BR>
 [https://www.gwern.net/Tanks The Tank Story] <BR>
-=== Gaussian Processes ===
+== Gaussian Processes ==
 [https://distill.pub/2019/visual-exploration-gaussian-processes/ Gaussian processes] - Visual exploration of Gaussian processes<BR>
 [http://www.infinitecuriosity.org/vizgp/ Gaussian processes] - Interactive Gaussian process visualization <BR>
@@ Line 47: / Line 47: @@
 [https://www.youtube.com/watch?v=4vGiHC35j9s Gaussian processes] - Introduction to Gaussian Processes Video Lecture (Nando de Freitas, 2013) <BR>
-=== Generative Adversarial Networks ===
+== Generative Adversarial Networks ==
 [https://medium.com/@jonathan_hui/gan-gan-series-2d279f906e7b GAN Series]; comprehensive overview of Generative Adversarial Networks<BR>
-=== Foundation Models: Large Language Models & Multimodal Models ===
+== Foundation Models: Large Language Models & Multimodal Models ==
 (Also see [[#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[#Limitations_of_AI|Limitations of AI]])
@@ Line 81: / Line 81: @@
 [[File:new.jpg]] [https://www.ibm.com/think/topics/mamba-model What is a Mamba model?] <BR>
-=== Physics Informed Machine Learning ===
+== Physics Informed Machine Learning ==
 [https://www.youtube.com/watch?v=JoFW2uSd3Uo High Level Overview of AI and ML in Science and Engineering] <BR>
-=== Recurrent Neural Networks ===
+== Recurrent Neural Networks ==
 [https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21 Illustrated guide to LSTMs and GRUs: a step by step explanation]<BR>
 [https://developer.ibm.com/tutorials/iot-deep-learning-anomaly-detection-1/ Introducing Deep Learning and Long Short-Term Memory Networks]<BR>
@@ Line 92: / Line 92: @@
 [http://colah.github.io/posts/2015-08-Understanding-LSTMs/ Understanding LSTMs]<BR>
-=== Reinforcement Learning ===
+== Reinforcement Learning ==
 [https://lilianweng.github.io/posts/2018-02-19-rl-overview/ A (Long) Peek into Reinforcement Learning] <BR>
 [https://bair.berkeley.edu/blog/2017/09/12/learning-to-optimize-with-rl/ Learning to Optimize with Reinforcement Learning] and learning to learn <BR>
 [https://arxiv.org/abs/1606.01885 Learning to Optimize] <BR>
-=== Robot Learning ===
+== Robot Learning ==
-−
 [https://www.i-aida.org/resources/robot-learning/ Robot Learning] a talk by Jan Peters <BR>
 [https://sites.google.com/view/hirl-education/home Human-Interactive Robot Learning] a course developed in [https://www.humane-ai.eu/project/tmp-038/ Micro Project TMP-038] as part of the [https://www.humane-ai.eu HumanE-AI-Net Network of Excellence] (click the <strong>Home</strong> text at the top-right of the page to access the slides)<BR>
-=== Self-Supervised Learning ===
+== Self-Supervised Learning ==
 [https://project.inria.fr/paiss/files/2018/07/zisserman-self-supervised.pdf Self-supervised Learning] Andrew Zisserman <BR>
 [https://medium.com/syncedreview/yann-lecun-cake-analogy-2-0-a361da560dae Yann LeCun Cake Analogy 2.0]; the slides from his ISCC talk are
 [https://twitter.com/ylecun/status/1097532314614034433 here] and the video of the talk is [http://isscc.org/2019-videos/ here]<BR>
-=== Transformers ===
+== Transformers ==
 [https://proceedings.neurips.cc/paper_files/paper/2023/file/57a9b97477b67936298489e3c1417b0a-Paper-Conference.pdf Energy Transformer] NeurIPS 2023 (note: Energy Transformers are not the same as Energy-Based Transformers)<BR>
 [https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 (Note: Energy-Based Transformers are not the same as Energy Transformers)<BR>