An enough week
blog.mitrichev.ch·3d·
Discuss: blog.mitrichev.ch
📈Linear programming
Math that feels good: creating learning resources for blind students
aimath.org·15h
✋Tactile Computing
LLM Optimization Notes: Memory, Compute and Inference Techniques
gaurigupta19.github.io·6d·
Discuss: Hacker News
💻Local LLMs
Everyday AI Agents
oreilly.com·2d
🤖AI Curation
Stop Worrying and Love the Bomb
bitbytebit.substack.com·1d·
Discuss: Substack
⚙️Build Archaeology
Assessing Paleovirus Revival Risk via Multi-Agent Bayesian Network Simulation
dev.to·1d·
Discuss: DEV
🦴Database Paleontology
DeepEN: Personalized Enteral Nutrition for Critically Ill Patients using Deep Reinforcement Learning
arxiv.org·2d
🧠Machine Learning
The Case for Separating Thinking (GPU) and Compute (CPU)
gojiberries.io·22h·
Discuss: Hacker News
⚡Z3 Optimization
Unlock Deep Learning Stability: Navigate the Activation Function Galaxy with 9 Dimensions!
dev.to·1d·
Discuss: DEV
🧠Machine Learning
Adaptive Predictive Maintenance of PLC-Controlled Conveyor Systems via Multi-Modal Data Fusion and Anomaly Scoring
dev.to·4d·
Discuss: DEV
🌊Stream Processing
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·3d·
Discuss: DEV
📊Multi-vector RAG
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
arxiv.org·5d
💻Local LLMs
Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
arxiv.org·3d
🛡Cybersecurity
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
arxiv.org·4d
🧮Kolmogorov Complexity
Enhanced Parasitic R/L Extraction in Die-Stacked ICs via Adaptive Finite Element Modeling and Bayesian Optimization
dev.to·1d·
Discuss: DEV
⚡Circuit Archaeology
Stop “Vibe Coding”: What Worked for Me as a Front-End Tech Lead
dev.to·20h·
Discuss: DEV
⚡Proof Automation
Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media
arxiv.org·2d
💾Binary Linguistics
Tech With Tim: How to Build AI Agents in Python
dev.to·14h·
Discuss: DEV
🔲Cellular Automata
Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
arxiv.org·3d
🎬AV1 Encoding
Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"
arxiv.org·3d
🧠Intelligence Compression