e-means: outperforming k-means (in one-tenth the epochs)
cs.LG, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/cwida/SuperKMeans
Project page: https://e-means.github.io
Terminology
Sources
- Scalable k-Means Clustering via Lightweight Coresets
- Scalable K-Means++
- High Fidelity Neural Audio Compression
- Jukebox: A Generative Model for Music
- The 2021 Image Similarity Dataset and Challenge
- High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations
- KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
- VIBE: Vector Index Benchmark for Embeddings
- Adam: A Method for Stochastic Optimization
- ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression
- FP8 Formats for Deep Learning
- Nomic Embed: Training a Reproducible Long Context Text Embedder
- Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence
- DINOv3
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding
- Flash-KMeans: Fast and Memory-Efficient Exact K-Means
- Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning