๐Ÿฟ๏ธ ScourBrowse
LoginSign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
๐Ÿ—๏ธ AI Infrastructure

Model Serving, GPU Clusters, Inference Optimization, MLOps

Keynote: Fine-tuning our way towards openness in AI - DevConf.CZ 2025
youtube.comยท14h
๐Ÿ Self-hosted AI
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
arxiv.orgยท1d
๐Ÿ’ปLocal LLMs
Powering Smarter AI with Precision โ€” Image Data Annotation at AkbhcodeAI
dev.toยท1dยท
Discuss: DEV
๐ŸคFederated Learning
Programming, Not Prompting: A Hands-On Guide to DSPy
towardsdatascience.comยท2d
๐Ÿค–AI agents
N8N, Local LLM, MCP proxy in 1 compose file
ajeetraina.comยท1dยท
Discuss: Hacker News
๐ŸงฉNomad
Machine Learning Fundamentals: active learning
dev.toยท1dยท
Discuss: DEV
๐ŸคFederated Learning
Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning
arxiv.orgยท1d
๐ŸŽ™๏ธWhisper
Stop Chasing โ€œEfficiency AI.โ€ The Real Value Is in โ€œOpportunity AI.โ€
towardsdatascience.comยท12h
๐Ÿง AI
Learnings from two years of using AI tools for software engineering
newsletter.pragmaticengineer.comยท1dยท
Discuss: Hacker News
๐ŸงฉLow-code
DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts
arxiv.orgยท1d
๐Ÿ‘ฅDigital Twins
Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
arxiv.orgยท1h
๐Ÿ Self-hosted AI
Build an agentic multimodal AI assistant with Amazon Nova and Amazon Bedrock Data Automation
aws.amazon.comยท2d
๐ŸงฉLow-code
We Gave Our Engineers AI. Here's What Happened.
dev.toยท14hยท
Discuss: DEV
๐ŸงฉLow-code
Unleashing AI/ML Inference: The Power of WebAssembly and WASI at the Edge
dev.toยท2dยท
Discuss: DEV
๐ŸงฉWebAssembly
Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
arxiv.orgยท1h
๐ŸŽ™๏ธWhisper
AI in the Cloud: Optimizing and Future-Proofing Your Strategy
dev.toยท1dยท
Discuss: DEV
๐Ÿ Self-hosted AI
RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1
arxiv.orgยท1d
๐Ÿ Self-hosted AI
Bilinear MLPs enable weight-based mechanistic interpretability
arxiv.orgยท1h
๐Ÿ’ปLocal LLMs
MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications
arxiv.orgยท1d
๐Ÿง AI
NaviAgent: Bilevel Planning on Tool Dependency Graphs for Function Calling
arxiv.orgยท1d
๐Ÿ”Query Compilers
Loading...Loading more...
AboutBlogChangelogRoadmap