Pith. sign in

REVIEW 7 cited by

Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.11637 v1 pith:C27DAN36 submitted 2019-12-25 cs.CL cs.LG

Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection

classification cs.CL cs.LG
keywords explicitsparsetransformerattentionmodellanguageablecontext
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of irrelevant information in the context. To tackle the problem, we propose a novel model called \textbf{Explicit Sparse Transformer}. Explicit Sparse Transformer is able to improve the concentration of attention on the global context through an explicit selection of the most relevant segments. Extensive experimental results on a series of natural language processing and computer vision tasks, including neural machine translation, image captioning, and language modeling, all demonstrate the advantages of Explicit Sparse Transformer in model performance. We also show that our proposed sparse attention method achieves comparable or better results than the previous sparse attention method, but significantly reduces training and testing time. For example, the inference speed is twice that of sparsemax in Transformer model. Code will be available at \url{https://github.com/lancopku/Explicit-Sparse-Transformer}

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connect...

  2. Value-Aware Stochastic KV Cache Eviction for Reasoning Models

    cs.LG 2026-06 unverdicted novelty 6.0

    VaSE improves KV cache eviction accuracy for reasoning models by over 4% versus prior eviction methods at 4x compression through value-magnitude protection and stochastic diversity.

  3. EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0

    EmambaIR is a visual state space model with cross-modal top-k sparse attention and gated SSM components that outperforms prior CNN and ViT methods on event-guided deblurring, deraining, and HDR reconstruction while re...

  4. Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding

    cs.AR 2026-04 unverdicted novelty 6.0

    Salca is a new ASIC accelerator that achieves 3.82× speedup and 74.19× energy efficiency over A100 for long-context attention via dual-compression dynamic sparse attention and pipelined hardware.

  5. TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs

    cs.LG 2026-02 unverdicted novelty 6.0

    TempoNet uses a slack-quantized Transformer with deep Q-learning and sparse attention to improve deadline fulfillment rates over traditional and neural schedulers in mixed-criticality real-time workloads.

  6. MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

    cs.CL 2025-07 unverdicted novelty 6.0

    MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.

  7. SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs

    cs.LG 2026-06 unverdicted novelty 5.0

    SoftMoE replaces discrete top-k routing in MoE LLMs with a truncated soft top-k LapSum relaxation, enabling differentiable optimization, learned non-uniform expert allocation across layers under a budget constraint, a...