Zhen Qin

papers

689

total citations

papers (14)

Transformer Memory as a Differentiable Search Index

NEURIPS 2022arXiv

375

citations

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

NEURIPS 2023arXiv

122

citations

Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes

ICML 2024arXiv

citations

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

ICML 2024arXiv

citations

Fine-Grained Audible Video Description

CVPR 2023arXiv

citations

Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective

AAAI 2024arXiv

citations

Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

AAAI 2025arXiv

citations

Elucidating the Design Space of Decay in Linear Attention

COLM 2025arXiv

citations

Zhen Qin

papers (14)

Transformer Memory as a Differentiable Search Index

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

Fine-Grained Audible Video Description

Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

Error Analysis of Tensor-Train Cross Approximation

Exploring Transformer Extrapolation

Learning List-Level Domain-Invariant Representations for Ranking

RD-Suite: A Benchmark for Ranking Distillation

Hybrid Latent Reasoning via Reinforcement Learning

Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Elucidating the Design Space of Decay in Linear Attention

papers (14)

Transformer Memory as a Differentiable Search Index

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

Fine-Grained Audible Video Description

Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

Error Analysis of Tensor-Train Cross Approximation

Exploring Transformer Extrapolation

Learning List-Level Domain-Invariant Representations for Ranking

RD-Suite: A Benchmark for Ranking Distillation

Hybrid Latent Reasoning via Reinforcement Learning

Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Elucidating the Design Space of Decay in Linear Attention