TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning
arxiv.org·5h
🗂️Vector Databases
NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit
developer.nvidia.com·1d·
Discuss: Hacker News
🧠Learned Codecs
k-NN Classification and Model Evaluation
dev.to·2h·
Discuss: DEV
🧠Machine Learning
Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
arxiv.org·5h
🧠Neural Codecs
Paying attention to feature distribution alignment (pun intended)
alexshtf.github.io·1d·
Discuss: Hacker News
📐Linear Algebra
How much power does gzip save on IoT web access?
bitbanksoftware.blogspot.com·21h·
Discuss: Lobsters, Hacker News
📦Deflate
Quality Precision
lesswrong.com·15h·
Discuss: Hacker News
✅FLAC Verification
Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
arxiv.org·5h
⧗Information Bottleneck
A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond
arxiv.org·5h
📊Learned Metrics
HV Metric For Time-Domain Full Waveform Inversion
arxiv.org·5h
⚙️Tape Engineering
Convergence and Generalization of Anti-Regularization for Parametric Models
arxiv.org·5h
🧠Machine Learning
Structural Damage Detection Using AI Super Resolution and Visual Language Model
arxiv.org·5h
🤖Advanced OCR
E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
arxiv.org·5h
🧠Machine Learning
MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
arxiv.org·5h
🧮Kolmogorov Complexity
AI Product Value Assessment Model: An Interdisciplinary Integration Based on Information Theory, Economics, and Psychology
arxiv.org·5h
🧠Intelligence Compression
Large Language Model-Based Automatic Formulation for Stochastic Optimization Models
arxiv.org·5h
🧠Machine Learning
An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation
arxiv.org·5h
📊Learned Metrics
Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data
arxiv.org·5h
🏺Computational Archaeology
Learning ON Large Datasets Using Bit-String Trees
arxiv.org·5h
🗂️Vector Databases
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
arxiv.org·5h
🤝Consensus Algorithms