The problem: most LLM neurons are uninterpretable, stopping us from mechanistically understanding the models. In October, we showed that dictionary learning could decompose a small model into "monosemantic" components we call "features"—making the model more interpretable.
RESEARCH
-
Yi-Large Ranks #7 Overall and Ties #1 in Chinese on Chatbot Arena
By
–
Thanks 15K+ real user votes on @lmsysorg chatbot arena showing strong results of Yi-Large: #7 in "overall" and tie #1 with @OpenAI GPT-4o in "Chinese." We also found hard prompts, long query, coding useful to challenge LLMs IQs. Try blind test on: https://
arena.lmsys.org -
Deploy AI Models to Edge Devices with On-Device AI Course
By
–
Learn to deploy AI models to edge devices in our new short course Introduction to On-Device AI, created with @Qualcomm and taught by Senior Director of Engineering @krishna_srd.
— Andrew Ng (@AndrewYNg) 21 mai 2024
I think on-device (edge) AI is an important technology trend that's enabling new low latency,… pic.twitter.com/Y76fQNWl55Learn to deploy AI models to edge devices in our new short course Introduction to On-Device AI, created with @Qualcomm and taught by Senior Director of Engineering @krishna_srd
. I think on-device (edge) AI is an important technology trend that's enabling new low latency, -
Mastering Recommendation Systems: A Complete Guide
By
–
Ever wondered how Spotify, YouTube, Netflix, or Amazon know just what you like? It's all thanks to recommendation systems!https://t.co/HSt9hBJSt8
— Satya Mallick (@LearnOpenCV) 21 mai 2024
Our latest blog "Mastering Recommendation Systems: A Complete Guide" breaks down what a recommendation system is and how it works.… pic.twitter.com/dAPNxzXlhfEver wondered how Spotify, YouTube, Netflix, or Amazon know just what you like? It's all thanks to recommendation systems! https://
learnopencv.com/recommendation
-system/
… Our latest blog "Mastering Recommendation Systems: A Complete Guide" breaks down what a recommendation system is and how it works. -
RAG Knowledge Graphs: Detailed Technical Walkthrough
By
–
detailed walkthrough of how to RAG against knowledge graphs
-
Training Time vs Committee Discussions on Voice Selection
By
–
this will take like 2 hrs of training, 2000 hours of committees on what voice to train
-
Yi-Large Ranks #7 on LMSYS Leaderboard
By
–
We're thrilled to see Yi-Large securing the #7 spot on @lmsysorg
's leaderboard! Thanks to all who voted and supported us. This is just the beginning!Check out the full leaderboard here and vote if you haven't already: http://
leaderboard.lmsys.org -
NVIDIA joins $110M US-Japan AI research partnership
By
–
NVIDIA joined a $110 million AI partnership between Japan and the United States that includes an initiative to fund research through a collaboration between the University of Washington and the University of Tsukuba. Learn more: https://
nvda.ws/3QRLJpr. -
Deloitte Intel Framework Optimizes AI Workloads and Choices
By
–
The more you learn about AI, the more you’ll be prepared for the future. @Deloitte and @intel have developed a fit-for-purpose hardware and software framework and methodology to optimize AI workloads and – best of all – simplify the vast sea of choices. Are you considering AI
-
Neural Pathways: Connections and Sparsity in Network Training
By
–
It's an homage to neural pathways, which seemed appropriate since neural network training is all about making connections between neurons (and also coveys sparsity, which we were/are interested in). "Neural pathways are the connections between neurons that light up when you