To be clear, this is a research model not yet deployed for the production vehicle fleet.
MACHINE LEARNING
-
Turbo LoRA Enhancement: 2x Throughput Boost Without Retraining
By
–
-
PARTNR: New Benchmark for Human-Robot Collaboration Tasks
By
–
Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities
— AI at Meta (@AIatMeta) 31 octobre 2024
By… pic.twitter.com/ga5MXRwtoXAdditionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By
-
Learned Vision Modules and Traditional Engineering for Robot Dexterity
By
–
Nice demo! Learned modules for vision plus GOFE (good old fashioned engineering). Some dexterity and impressive body joint coordination. (I like the “Fully Autonomous” text in the corner.) As you noted Chris: “no end-to-end stuff.” 😉 https://t.co/yTiFQcGTQN
— Ken Goldberg (@Ken_Goldberg) 31 octobre 2024Nice demo! Learned modules for vision plus GOFE (good old fashioned engineering). Some dexterity and impressive body joint coordination. (I like the “Fully Autonomous” text in the corner.) As you noted Chris: “no end-to-end stuff.” 😉
-
AI Prompt Engineering: A Deep Dive into LLM Optimization
By
–
AI prompt engineering: A deep dive https://
bit.ly/3ZNUExp
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
MATLAB Uncovers Greater Horseshoe Bat Navigation Behavior
By
–
🦇 We're taking off with BATLAB! 🐸
— MathWorks (@MathWorks) 31 octobre 2024
Did you know greater horseshoe bats leapfrog to find their way home? These bug-eating champs rely on their position relative to other bats for safety & efficiency.
Find out how MATLAB helped uncover this behavior! 🔗 https://t.co/6I40GH5Dci pic.twitter.com/ozyHFVZClkWe're taking off with BATLAB! Did you know greater horseshoe bats leapfrog to find their way home? These bug-eating champs rely on their position relative to other bats for safety & efficiency. Find out how MATLAB helped uncover this behavior! https://
spr.ly/6013SrU5P -
Python and PyTorch prerequisites for machine learning course
By
–
Thanks for your interest! I'd say familiarity with Python programming would be required. Ideally some light machine learning or deep learning background with PyTorch. However, I do have a ~40-page introduction to the essentials (Appendix A), which could get you up to speed quick
-
Highlights from OpenAI DevDay: image model, o1 coding paradigm, Realtime API
By
–
> Highlights from yesterday’s @OpenAI DevDay in London: image model in the works, o1’s new coding paradigm, Realtime API o1 creates a new paradigm for code. OpenAI devs seem to have massively adopted o1 + Cursor, seems like the experience is vastly improved compared to GH
-
VRAM Requirements for AI Models Across Hardware Architectures
By
–
It should work on CPU/ CUDA/ MPS across backends, w.r.t hardware requirements: 1B should take roughly 2GB VRAM to load in fp16/ bf16.
600M should take 1.2 GB VRAM
350M – ~700MB VRAM
125 – ~250MB VRAM Ofcourse at lower quants Q4/ Q8 you reduce this even further. -
Meta Releases MobileLLM: Depth Critical Over Width
By
–
Meta released MobileLLM – 125M, 350M, 600M, 1B model checkpoints! Notes on the release: Depth vs. Width: Contrary to the scaling law (Kaplan et al., 2020), depth is more critical than width for small LLMs, enhancing abstract concept capture and final performance Embedding