» Tag
machine-learning
163 postsFiltered Vector Search: What Acorn Fixes, and What Fixes Acorn
Qdrant introduces new methods to solve filtered vector search issues. ACORN and filterable HNSW enhance performance.
No cloud, no GPUs: Liquid AI's LFM2.5-2.6B model empowers edge devices
Liquid AI introduces LFM2.5-2.6B, a model that runs on local hardware without cloud or GPU dependencies.
NVIDIA VoiceChat-11B: AI Speech Model for Real-Time Communication
NVIDIA VoiceChat-11B is an AI speech model with 11 billion parameters, designed for real-time voice interactions.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comAnatomy of an AI Kill Chain – Airwars X AI Now Institute
Military AI is reducing human oversight, increasing risks. An abstract kill chain illustrates these concerns.
Federated Learning Project Reveals High Accuracy Can Mislead Detection
A federated learning comparison shows that high global accuracy can mask poor detection performance.
Moonshot AI's Kimi K3 Model Surpasses Claude Fable 5 in Benchmark
Moonshot AI introduces Kimi K3, a 2.8 trillion parameter model excelling in coding benchmarks.
Differentiable Fortran Applications with LFortran and Enzyme
Exploring methods for automatic differentiation from Fortran simulation code using LFortran and Enzyme.
Beyond Grep: The Need for Context-Rich AI Coding Tools
Vinay Perneti of Augment Code discusses the significance of context-rich AI coding tools.
Solving Moe Load Imbalance in LLM Training via Optimal Transport
TAOT method improves MoE training speed by 43% while reducing communication costs by 74%.
1.5B Model Trained to Write Shell Commands on a Laptop CPU
User trains a 1.5B Qwen2.5-Coder model to generate shell commands. It operates on a laptop.