LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
docker.com·1d
💻Local LLMs
Context Matters: Learning Global Semantics for Visual Reasoning and Comprehension
arxiv.org·3d
🏛Digital humanities
Grouped Differential Attention
arxiv.org·2d
⧗Information Bottleneck
Curriculum Learning with Synthetic Data for Enhanced Pulmonary Nodule Detection in Chest Radiographs
arxiv.org·1d
👁️OCR Enhancement
Cluster Paths: Navigating Interpretability in Neural Networks
arxiv.org·2d
🧠Machine Learning
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
arxiv.org·1d
🧠Machine Learning
Why LLMs cannot reach GenAI, but why it looked like they could
haversine.substack.com·6h·
Discuss: Substack
🧠Intelligence Compression
FrameOracle: Learning What to See and How Much to See in Videos
arxiv.org·4d
📊Rate-Distortion Theory
TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning
arxiv.org·2d
🔨Compilers
Automated Spectral Fingerprint Deconvolution for Polymer Identification via Deep Oligomer Networks
dev.to·4h·
Discuss: DEV
🌈Spectroscopy
INFER : Learning Implicit Neural Frequency Response Fields for Confined Car Cabin
arxiv.org·1d
👂Psychoacoustic Coding
Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
arxiv.org·1d
🧠Machine Learning
Learning a distance measure from the information-estimation geometry of data
arxiv.org·5d
📐Information Geometry
Seeing the Future: Mastering Action Recognition with Recurrence-Complete Architectures
dev.to·1d·
Discuss: DEV
🌊Streaming Algorithms
NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering
arxiv.org·3d
📊Quantization
From RNNs to ChatGPT: The Paper That Changed How AI Thinks 🤖
dev.to·12h·
Discuss: DEV
🎧Learned Audio
TTRV: Test-Time Reinforcement Learning for Vision Language Models
arxiv.org·2d
🗜️LZW Variants
LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation
arxiv.org·1d
🧮Vector Embeddings
Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
arxiv.org·1d
🧠Machine Learning
Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
arxiv.org·3d
🌀Differential Geometry