📱 Edge AI

Model Quantization, ONNX Runtime, Embedded Inference, TinyML

Hypernetworks: Neural Networks for Hierarchical Data
sturdystatistics.com·4d
🤝Federated Learning
Ghosts in the Code: A Memorial Grove for Deleted AI
connectingminds.uk·2d·
Discuss: DEV, Hacker News
🧠AI
VLLM Predicted Outputs
cascadetech.ai·23h·
Discuss: Hacker News
💻Local LLMs
Show HN: I built a local AI agent desk toy
blog.simone.computer·2d·
Discuss: Hacker News
🎙️Whisper
Automated Anomaly Detection in Account Takeover via Multi-Modal Graph Neural Network Fusion
dev.to·15h·
Discuss: DEV
💻Local LLMs
Beyond Transformers: Can MLPs Unlock the Potential of In-Context Learning?
dev.to·3d·
Discuss: DEV
🏗️AI Infrastructure
**The Quantum Leap in Neural Networks: Revolutionizing Compu
dev.to·1h·
Discuss: DEV
🧠Neuromorphic Hardware
Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization
arxiv.org·2d
🏗️AI Infrastructure
Optimal Stopping in Latent Diffusion Models
arxiv.org·1d
💻Local LLMs
94% of Developers Waste Tokens on Reasoning LLMs. Here's Why.
dev.to·1d·
Discuss: DEV
🤖AI agents
Krish Naik: Agentic AI 3.0 - Live Ultimate RAG Bootcamp Course Announcement
dev.to·11h·
Discuss: DEV
🤖AI agents
🧠 Real-Time Smart Speech Assistant with Python, Whisper & LLMs
dev.to·22h·
Discuss: DEV
🎙️Whisper
🚀 The Startup Technical Guide to Building AI Agents (with Google Cloud)
dev.to·1d·
Discuss: DEV
🤖AI agents
Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs
arxiv.org·4d
🤖AI agents
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
💻Local LLMs
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arxiv.org·1d
💻Local LLMs
Real-Time Anomaly Attribution via Hybrid Graph Neural Network & Causal Inference
dev.to·2d·
Discuss: DEV
🏗️AI Infrastructure
100 Poisoned Examples Can Hijack Any AI Model (Even GPT-4-Scale LLMs)
dev.to·2d·
Discuss: DEV
💻Local LLMs
Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
arxiv.org·1d
🧠Neuromorphic Hardware
High-Throughput Reactive Sputtering Process Optimization via Adaptive Machine Learning Control
dev.to·4h·
Discuss: DEV
🏗️AI Infrastructure