YouTube gets ~5% CTR lift on Shorts by replacing embedding tables with Semantic IDs
shaped.ai·1d
📊Feed Optimization
The key to conversational speech recognition
datasciencecentral.com·2d
🎵Audio ML
Loyca.ai – An open-source, local-first AI assistant with contextual awareness
github.com·1h·
Discuss: Hacker News
🌀Brotli Internals
AI as both authors and reviewers of research papers
openreview.net·1d·
Discuss: Hacker News
🔲Cellular Automata
Hyper-Personalized Cyberbullying Mitigation via Adaptive Linguistic Fingerprinting and Behavioral Anomaly Detection
dev.to·9h·
Discuss: DEV
🎛️Feed Filtering
Approximate Gaussianity Beyond Initialisation in Neural Networks
arxiv.org·3d
🕸️Tensor Networks
Automated Spectral Fingerprint Deconvolution for Polymer Identification via Deep Oligomer Networks
dev.to·18h·
Discuss: DEV
🌈Spectroscopy
Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions
arxiv.org·4d
📈Linear programming
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·1d
⚡Proof Automation
Probabilistically-Safe Bipedal Navigation over Uncertain Terrain via Conformal Prediction and Contraction Analysis
arxiv.org·1d
🌀Differential Geometry
Dynamic Adaptive Redundancy Allocation via Hierarchical Bayesian Optimization
dev.to·1d·
Discuss: DEV
💾Storage Replication
Scalable Semantic Map Generation via Hierarchical Graph Optimization
dev.to·23h·
Discuss: DEV
⚡Incremental Computation
DPA-Net: A Dual-Path Attention Neural Network for Inferring Glycemic Control Metrics from Self-Monitored Blood Glucose Data
arxiv.org·2d
🧠Machine Learning
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
arxiv.org·1d
🌀Differential Geometry
Latency vs. Accuracy for LLM Apps — How to Choose and How a Memory Layer Lets You Win Both
dev.to·4d·
Discuss: DEV
⚡Performance Mythology
Reinforcement Learning from Probabilistic Forecasts for Safe Decision-Making via Conditional Value-at-Risk Planning
arxiv.org·1d
🧠Machine Learning
Quantum Relative Entropy Decay Composition Yields Shallow, Unstructured k-Designs
arxiv.org·1d
⚛️Quantum Circuits
Learning Pareto-Optimal Pandemic Intervention Policies with MORL
arxiv.org·4d
🔲Cellular Automata
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.org·3d
💨Cache Optimization
Less Is More: Recursive Reasoning with Tiny Networks
github.com·3d·
Discuss: Hacker News
📊Quantization