NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
computational burden
4 papers
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Online Segment Any 3D Thing as Instance Tracking
QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks