Reinforcement Learning of Large Language Models, Spring 2025(UCLA) Great set of new lectures on reinforcement learning of LLMs. Covers a wide range of topics related to RLxLLMs such as basics/foundations, test-time compute, RLHF, and RL with verifiable rewards(RLVR).
MACHINE LEARNING
-
Stanford Free AI and Machine Learning YouTube Courses Available
By
–
Find YouTube links in the thread below for Stanford's FREE Courses on #AI and #MachineLearning … #DataScientist #DataScience #ML RT @swapnakpanda
-
Decades of RL Failure to Learn Macros Continues
By
–
Also, RL folks have been trying to learn macros (“options”, as Rich Sutton calls them) and failing for decades. But any day now . . .
-
Explanation-Based Learning Resurfaces as RL Alternative
By
–
Andrej rediscovers explanation-based learning, which was hot until RL displaced it.
-
Intelligence Transfer Across Domains: Generalization Mystery and Evidence
By
–
I still find it mysterious whether and how intelligence and capabilities transfer between domains and skills – from meta learning during early days to more recent question like whether solving maths helps writing a good essay. Sometime I feel a bit pessimistic given not enough evidence I’ve seen. Would like to get more suggestions and pointers to papers on this topic of generalization in the thread! 🧵
→ View original post on X — @lilianweng, 2025-07-13 21:19 UTC
-
Thousand-Brains Systems: Sensorimotor Intelligence for Rapid Learning
By
–
Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference Leadholm et al.: https://
arxiv.org/abs/2507.04494 #ArtificialIntelligence #DeepLearning #MachineLearning -
Amiga 1000 powered early tensor engine Lush development
By
–
True story.
I used this particular Amiga 1000 to write SN (Léon had his own Amiga) using Emacs and gcc, and to write my PhD thesis with Emacs and LaTeX in 1987.
SN, later evolved into SN2 and SN3, and was open sourced under the name Lush in 2001.
SN3/Lush (tensor engine with Lisp -
Convolutional Neural Network Implementation on SN-1 Hardware 1988
By
–
That convolutional net was implemented in SN-1, which was initially developed on this Amiga (and Léon's).
Training runs were executed on a Sun 4 at Bell Labs in late 1988. -
SN-1 Software: Training First LeNets in Deep Learning
By
–
SN-1 is the software I used to implement and train the first LeNets.
-
LeNet Implementation History: SN-1 Development and Early Neural Networks
By
–
LeNet was implemented in late 1988 using SN-1 originally developed on this Amiga and on Léon's Amiga.
I finished SN during my postdoc at the University of Toronto, implemented shared weights and a graphic output.
Experiments were run on a Sun 4 at Bell Labs in late 1988.