Lune

Profiles2020-2025

Tianlong Chen

University of Texas at Austin

44Papers
1Last author
75Unique co-authors
12First author
0Solo

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

Recent papers44

  1. Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive StudyAuthor 2 of 5AAAI 2025
  2. TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion ModelsAuthor 4 of 5CVPR 2024
  3. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language ModelsAuthor 4 of 12NeurIPS 2023 · 1,003 citations
  4. AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-ExpertsAuthor 1 of 8ICCV 2023 · 119 citations
  5. The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that MatterAuthor 3 of 4NeurIPS 2023 · 57 citations
  6. Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-ExpertsAuthor 5 of 8ICCV 2023 · 36 citations
  7. Is Attention All That NeRF Needs?Author 4 of 6ICLR 2023 · 6 citations
  8. Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable TransformersAuthor 1 of 5ICLR 2023 · 6 citations
  9. DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language ModelsAuthor 2 of 6ACL 2023 · 4 citations
  10. Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!Author 2 of 7ICLR 2023 · 1 citation
  11. M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-AdaptationAuthor 3 of 5ICLR 2023
  12. Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to PracticeAuthor 3 of 4ICLR 2022 · 212 citations
  13. M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designAuthor 5 of 9NeurIPS 2022 · 152 citations
  14. The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse TrainingAuthor 2 of 7ICLR 2022 · 141 citations
  15. Unified Visual Transformer CompressionAuthor 2 of 8ICLR 2022 · 118 citations
  16. Augmentations in Hypergraph Contrastive Learning: Fabricated and GenerativeAuthor 3 of 6NeurIPS 2022 · 96 citations
  17. Playing Lottery Tickets with Vision and LanguageAuthor 4 of 9AAAI 2022 · 64 citations
  18. Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityAuthor 2 of 9ICLR 2022 · 62 citations
  19. Sparsity Winning Twice: Better Robust Generalization from More Efficient TrainingAuthor 1 of 7ICLR 2022 · 54 citations
  20. The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of RedundancyAuthor 1 of 5CVPR 2022 · 36 citations
  21. Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded AugmentationsAuthor 1 of 4CVPR 2022 · 32 citations
  22. Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean DatasetsAuthor 3 of 5NeurIPS 2022 · 21 citations
  23. Symbolic Learning to Optimize: Towards Interpretability and ScalabilityAuthor 2 of 4ICLR 2022 · 21 citations
  24. CADTransformer: Panoptic Symbol Spotting Transformer for CAD DrawingsAuthor 2 of 4CVPR 2022 · 19 citations
  25. Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great AgainAuthor 3 of 6NeurIPS 2022 · 17 citations
  26. Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for FreeAuthor 1 of 6CVPR 2022 · 13 citations
  27. Sparse Winning Tickets are Data-Efficient Image RecognizersAuthor 4 of 6NeurIPS 2022 · 9 citations
  28. Optimizer AmalgamationAuthor 2 of 6ICLR 2022 · 5 citations
  29. Chasing Sparsity in Vision Transformers: An End-to-End ExplorationAuthor 1 of 6NeurIPS 2021 · 295 citations
  30. Sparse Training via Boosting Pruning Plasticity with NeuroregenerationAuthor 2 of 10NeurIPS 2021 · 145 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines