Deploying AI on the edge? Then you know the challenge: preserving accuracy while shrinking your model footprint. Some of our community members are sharing quantisation workflows that really deliver, and others, like the awesome team at @DeGirum
, are doing impressive things on
MACHINE LEARNING
-
Edge AI Model Quantization: Shrinking Footprint While Preserving Accuracy
By
–
-
Video-RAG: Training-Free Retrieval for Long-Video LVLMs
By
–
📢☑️Video-RAG: Training-Free Retrieval for Long-Video LVLMs
— Satya Mallick (@LearnOpenCV) 18 août 2025
In this week’s deep dive, we implement Video-RAG as a training-free, single-pass pipeline and integrate it with LLaVA-Video-7B (Qwen2, 32K context), without APE – to keep things reproducible on today’s stacks. We enable… pic.twitter.com/ZVNMVXr0WQ-RAG: Training-Free Retrieval for Long-Video LVLMs In this week’s deep dive, we implement Video-RAG as a training-free, single-pass pipeline and integrate it with LLaVA-Video-7B (Qwen2, 32K context), without APE – to keep things reproducible on today’s stacks. We enable
-
LFM2-VL Support Added for GGUF and llama.cpp
By
–
LFM2-VL support with GGUF and llama.cpp 🥳
— Maxime Labonne @ ICLR (@maximelabonne) 18 août 2025
You can now run these tiny, hyper-efficient VLMs on your watch!
We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface pic.twitter.com/DfK3p1MA08LFM2-VL support with GGUF and llama.cpp You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface
-
JAX adoption challenges: GPU and TPU experience insights
By
–
the jax topic didn't even come to my table (I'm also out on leave). afaik the biggest pushback to using jax came from msl folks who had to use jax+gpus in their previous place of employment and didn't think it was great on a few important dimensions.
the jax+tpus experience -
Geometry-Based Machine Learning and Data Analysis in R
By
–
"The Shape of Data — Geometry-Based #MachineLearning and Data Analysis in R" http://
amzn.to/3JRxBZL ——
#Rstats #DataScientist #Mathematics #ML #AI #DataScience #NetworkScience -
Moderna and IBM Partner on Quantum Computing for mRNA Drug Design
By
–
Breakthrough: @moderna_tx and @IBM are teaming up to supercharge mRNA drug design using quantum computing. By leveraging variational quantum algorithms (VQAs), they’re tackling the challenge of predicting #mRNA secondary structures—key to accelerating next-gen therapies.
-
AI Model Evolution Safety and Training Infrastructure Challenges
By
–
Other AI research in last week's AI Lab newsletter: The evolutionary tree of AI models. How to stop chatbots learning to be unsafe. And the insane power needed for future AI training runs. …
-
Master Bayesian Statistics in Python with Think Bayes
By
–
Whether you’re a novice or an experienced data scientist, this article will equip you with the skills and understanding needed to harness the full potential of Think Bayes. https://
pyoflife.com/think-bayes-ba
yesian-statistics-in-python/
…
#DataScience #pythonprogramming #DataScientists #machinelearning #codinglife -
Impressive Collection of O’Reilly Machine Learning AI Data Science Books
By
–
See the impressive collection of @OReillyMedia #MachineLearning / #AI / #DataScience books at: http://
amzn.to/3icyoqJ -
Machine Learning for Tabular Data: XGBoost and Deep Learning Book
By
–
I have this excellent book from @ManningBooks >> #MachineLearning for Tabular Data: XGBoost, Deep Learning, and #AI, by @MarkRyanMkm & @lucamassaron Get it here: http://
amzn.to/41J8WA6 • Master XGBoost
• Apply deep learning to tabular data
• Deploy models locally and in the