EntmaxKV: Support-Aware Decoding for Entmax Attention
cs.LG, cs.CL
Submitted: 2026-05-20
Updated: 2026-09-26
Code: https://github.com/deep-spin/entmaxkv
Terminology
Sources
- MagicPIG: LSH Sampling for Efficient LLM Generation
- AdaSplash-2: Faster Differentiable Sparse Attention
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Kimi Linear: An Expressive, Efficient Attention Architecture
- Long-Context Generalization with Sparse Attention
- Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks