Treacherous vibrations: Eavesdropping on cell phone calls with radar and AI
heise.de·1d
🎙️Whisper
Practical Diff Testing of Stateful Applications (VLDB'25)
muratbuffalo.blogspot.com·4h·
Discuss: Hacker News
🔄Reproducible Builds
NZ1: A minimalist, dependency-free data compression algorithm
github.com·23h·
Discuss: Hacker News
🌊Streaming Compression
AI browsers share sensitive personal data, new study finds
euronews.com·22h·
Discuss: Hacker News
🔤EBCDIC Privacy
Show HN: Building a web search engine from scratch with 3B neural embeddings
blog.wilsonl.in·1d·
Discuss: Lobsters, Hacker News
🔍Semantic Search
Dynamic Digital Twin Calibration via Multi-Modal Anomaly Detection and Reinforcement Learning
dev.to·18h·
Discuss: DEV
👁️Observatory Systems
Dead Zone of Accountability: Why Social Claims in Machine Learning Research Should Be Articulated and Defended
arxiv.org·18h
🎯Performance Proofs
TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning
arxiv.org·18h
🔍Information Retrieval
FOBNN: Fast Oblivious Inference via Binarized Neural Networks
arxiv.org·1d
🔢Binary Embeddings
Fully-Fluctuating Participation in Sleepy Consensus
arxiv.org·1d
🤝Consensus Algorithms
Classifier Language Models: Unifying Sparse Finetuning and Adaptive Tokenization for Specialized Classification Tasks
arxiv.org·18h
🤖Grammar Induction
A Deep Dive into AI Inference Platforms – Part 1
procurefyi.substack.com·21h·
Discuss: Substack
⚡Incremental Computation
How Graphs Boost LLM Precision and Explainability in Cybersecurity
hackernoon.com·2d
💻Local LLMs
EGGCodec: A Robust Neural Encodec Framework for EGG Reconstruction and F0 Extraction
arxiv.org·18h
👂Psychoacoustic Coding
Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge
arxiv.org·18h
📊Feed Optimization
Numerical Considerations in Weighted Model Counting
arxiv.org·2d
📐Error Bounds
Automated Arthroscopic Image Segmentation & Anomaly Detection via Hierarchical, Federated Learning
dev.to·2h·
Discuss: DEV
🧠Machine Learning
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
arxiv.org·1d
💻Local LLMs
Algorithmic Deception Resilience via Adaptive Behavioral Profiling (ADB-Profile)
dev.to·2d·
Discuss: DEV
🎯Threat Hunting
SAEMark: Multi-bit LLM Watermarking with Inference-Time Scaling
arxiv.org·1d
⚙️Compression Benchmarking