#model-optimization

[ follow ]
#machine-learning #computer-vision #image-segmentation #runtime-deployment #llvm #ai-compilers #edge-ai
Artificial intelligence
fromInfoQ
3 days ago

SAM 3 Introduces a More Capable Segmentation Architecture for Modern Vision Workflows

SAM 3 improves segmentation accuracy, boundary quality, contextual coherence, robustness, and inference speed for reliable deployment across GPUs, mobile hardware, and web runtimes.
Artificial intelligence
fromHackernoon
55 years ago

Keep the Channel, Change the Filter: A Smarter Way to Fine-Tune AI Models | HackerNoon

Efficient fine-tuning of large pre-trained models can be achieved by adjusting only filter atoms while preserving overall model capabilities.
fromHackernoon
10 months ago

Chinese AI Model Promises Gemini 2.5 Pro-level Performance at One-fourth of the Cost | HackerNoon

MiniMax's M1 model stands out with its open-weight reasoning capabilities, scoring high on multiple benchmarks, including an impressive 86.0% accuracy on AIME 2024.
Artificial intelligence
fromHackernoon
5 months ago

Can Smaller AI Outperform the Giants? | HackerNoon

The advancement of vision-language models (VLMs) relies on foundational design choices, yet many lack justification, hindering progress by obscuring performance improvements.
Artificial intelligence
Growth hacking
fromInfoQ
6 months ago

Scaling Large Language Model Serving Infrastructure at Meta

LLM serving is evolving into a foundational technology similar to an operating system.
fromInfoWorld
1 year ago

All the brilliance of AI on minimalist platforms

Fast forward to 2024, our reliance on massive data infrastructures is evaporating, with AI systems running on palm-sized devices. Apple & Qualcomm chips integrate AI for tasks like language translation and photo processing.
Digital life
[ Load more ]