Lune

Profiles2021-2025

Zhenyu Zhang

The University of Texas at Austin

12Papers
0Last author
25Unique co-authors
2First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers12

  1. R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM InferenceAuthor 1 of 6ICLR 2025
  2. Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing PolicyAuthor 2 of 7ICLR 2024 · 97 citations
  3. JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and AttentionAuthor 3 of 5ICLR 2024 · 49 citations
  4. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language ModelsAuthor 1 of 12NeurIPS 2023 · 1,003 citations
  5. Are Large Kernels Better Teachers than Transformers for ConvNets?Author 3 of 8ICML 2023 · 18 citations
  6. Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable TransformersAuthor 2 of 5ICLR 2023 · 6 citations
  7. Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!Author 3 of 7ICLR 2023 · 1 citation
  8. The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of RedundancyAuthor 2 of 5CVPR 2022 · 36 citations
  9. Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean DatasetsAuthor 2 of 5NeurIPS 2022 · 21 citations
  10. Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for FreeAuthor 2 of 6CVPR 2022 · 13 citations
  11. Sparse Winning Tickets are Data-Efficient Image RecognizersAuthor 3 of 6NeurIPS 2022 · 9 citations
  12. You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownershipAuthor 3 of 4NeurIPS 2021 · 34 citations
Dusk over the sea between two cliffs drawn in fine vertical lines