🎵 Audio ML

Speech Recognition, Music Information Retrieval, Acoustic Modeling, Sound Classification

JavaScript Library Runs Machine Learning Models in Browser
thenewstack.io·3d
🏴󠁧󠁢󠁳󠁣󠁴󠁿Scottish Computing
Thinking Machines Lab co-founder Andrew Tulloch heads to Meta
techcrunch.com·4h
🏴󠁧󠁢󠁳󠁣󠁴󠁿Scottish Computing
​​Speech-to-Retrieval (S2R): A new approach to voice search
research.google·4d·
Discuss: Hacker News
🎙️Whisper
AI as both authors and reviewers of research papers
openreview.net·2d·
Discuss: Hacker News
🔲Cellular Automata
IBM Ships Homegrown “Spyre” Accelerators, Embraces Anthropic For AI Push
nextplatform.com·1d·
Discuss: Hacker News
🏴󠁧󠁢󠁳󠁣󠁴󠁿Scottish Computing
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
🔨Compilers
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·2d·
Discuss: DEV
📊Multi-vector RAG
ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
arxiv.org·1d
✨Effect Handlers
Self-Improving LLM Agents at Test-Time
arxiv.org·1d
🧠Intelligence Compression
GNN Predictions: Hidden Bugs and the Verification Nightmare by Arvind Sundararajan
dev.to·1d·
Discuss: DEV
⚙️Proof Engineering
Ensemble Deep Learning and LLM-Assisted Reporting for Automated Skin Lesion Diagnosis
arxiv.org·2d
🧠Machine Learning
Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"
arxiv.org·2d
🧠Intelligence Compression
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
arxiv.org·2d
🧠Intelligence Compression
To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
arxiv.org·1d
📊Learned Metrics
Reinforcement Learning from Probabilistic Forecasts for Safe Decision-Making via Conditional Value-at-Risk Planning
arxiv.org·1d
🧠Machine Learning
What is a Large Language Model (LLM)
dev.to·1d·
Discuss: DEV
💻Local LLMs
Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals
arxiv.org·2d
🏛Digital humanities
Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
arxiv.org·3d
🧮Kolmogorov Bounds
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·2d·
Discuss: DEV
📊Multi-vector RAG
Memory Retrieval and Consolidation in Large Language Models through Function Tokens
arxiv.org·1d
💻Programming languages