Skip to content
conftrace_

approximate attention

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sequence parallelism (2) efficient computing (2) attention mechanism (2) transformer model (1) long-range arena (1) top-k attention (1) context block (1) sequence length (1) long-context inference (1) value vector (1)

Papers

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention ACL 2026 APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs ACL 2025 HyperAttention: Long-context Attention in Near-Linear Time ICLR 2024 Multi Resolution Analysis (MRA) for Approximate Self-Attention ICML 2022 Memory-efficient Transformers via Top-k Attention EMNLP 2021 Value-aware Approximate Attention EMNLP 2021