No article text was recorded for this version.
top-k sparse attention
Version 1 of 155 papers63 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning
- Blog: SparQ Attention: Bandwidth-Efficient LLM Inference
- Blog: Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization
- Blog: Entroformer: A Transformer-based Entropy Model for Learned Image Compression
- Blog: Learning hybrid dynamic transformers for underwater image super-resolution
- Blog: Accelerated Inference with Long-Sequence Transformers on CPUs
- Blog: TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer
- Blog: Memory-efficient Transformers via Top-k Attention
- Blog: IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
- Blog: Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
- Blog: High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
- Blog: Modeling air quality PM2.5 forecasting using deep sparse attention-based transformer networks
- Blog: Pairwise Body-Part Attention for Recognizing Human-Object Interactions
- Blog: Surprisingly Easy Hard-Attention for Sequence to Sequence Learning
- Blog: X-former Elucidator: Reviving Efficient Attention for Long Context Language Modeling
- Blog: Guided Slot Attention for Unsupervised Video Object Segmentation
- Blog: Memory-Aware Attentive Control for Community Question Answering With Knowledge-Based Dual Refinement
- Blog: k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
- Blog: Memory Caching: RNNs with Growing Memory
- Blog: Prompt-Aware Controllable Shadow Removal
- Blog: Loki: Low-rank Keys for Efficient Sparse Attention
- Blog: DSSA-TCN: Exploiting adaptive sparse attention and diffusion graph convolutions in temporal convolutional networks for traffic flow forecasting
- Blog: SparseD: Sparse Attention for Diffusion Language Models
- Blog: Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems
- Blog: Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization
- Blog: High-Similarity-Pass Attention for Single Image Super-Resolution
- Blog: Modern Hopfield Networks and Attention for Immune Repertoire Classification
- Blog: Attentional Feature-Pair Relation Networks for Accurate Face Recognition
- Blog: Adaptive Memory Networks
- Blog: Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement
- Blog: Hierarchical Memory Networks
- Blog: InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting
- Blog: Kinetics: Rethinking Test-Time Scaling Law
- Blog: Re-Attentional Controllable Video Diffusion Editing
- Blog: Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
- Blog: KVT: k-NN Attention for Boosting Vision Transformers
- Blog: ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
- Blog: CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
- Blog: Enhancing Privacy in Large Language Model with Homomorphic Encryption and Sparse Attention
- Blog: Out of the Memory Barrier: A Highly Memory-Efficient Training System for LLMs with Million-Token Contexts
- Blog: Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs
- Blog: Optimizing Mixture of Block Attention
- Blog: Sharpness-aware Zeroth-order Optimization for Graph Transformers
- Blog: Unlimiformer: Long-Range Transformers with Unlimited Length Input
- Blog: HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices
- Blog: TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems
- Blog: SparseTT: Visual Tracking with Sparse Transformers
- Blog: Faithful Interpretation for Graph Neural Networks
- Blog: Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
- Blog: Graph Representation Learning via Hard and Channel-Wise Attention Networks
- Blog: Towards Robust Knowledge Tracing Models via k-Sparse Attention
- Blog: FAST-AR: Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
- Blog: MFCFlow: A Motion Feature Compensated Multi-Frame Recurrent Network for Optical Flow Estimation
- Blog: Kinetics: Rethinking Test-Time Scaling Laws
- Blog: LUXFormer: Low-light image enhancement via joint spatial-frequency illumination modeling
History & citation
Current · Permanent link
- This direction split from Sparsifying Transformers with Top-k Attention (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_top_k_sparse_attention_43d28597,
title = {top-k sparse attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/top-k-sparse-attention/rdr_43d28597f3b3461595147fd3db2728fd},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_top_k_sparse_attention_43d28597_v1,
title = {top-k sparse attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/top-k-sparse-attention/rdr_43d28597f3b3461595147fd3db2728fd/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}