quadratic complexity
Quadratic complexity refers to algorithms where the time or space requirements grow proportionally to the square of the input size, typically becoming less efficient as input sizes increase.
- CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
- Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis
- Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
- Flash Invariant Point Attention
- MVSMamba: Multi-View Stereo with State Space Model
- PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
- SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
- Two Heads are Better than One: Simulating Large Transformers with Small Ones
- VORTA: Efficient Video Diffusion via Routing Sparse Attention
- VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory