Attention in Constant Time: Vashista Sparse Attention for Long-Context Decoding with Exponential Guarantees
cs.AI, cs.LG, stat.ML
Submitted: 2026-02-14
Updated: 2026-11-09
Code: https://github.com/DatarConsulting/Vashista-Sparse-Attention
Terminology
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents