Hardware-aware Calibrated Clustered Attention for Efficient Visual Geometric Transformers
cs.CV, cs.LG
Submitted: 2026-10-07
Updated: 2026-10-07
Terminology
Sources
- XAttention: Block Sparse Attention with Antidiagonal Scoring
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- Generating Long Sequences with Sparse Transformers
- Ring Attention with Blockwise Transformers for Near-Infinite Context
- MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective
- Token Merging: Your ViT But Faster
- The Llama 3 Herd of Models
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models