Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
CoRR, March, 2025
Týr-the-Pruner: Unlocking Accurate 50% Structural Pruning for LLMs via Global Sparsity Distribution Optimization.
CoRR, March, 2025
Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility.
CoRR, March, 2025
Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE.
CoRR, February, 2025
MSWA: Refining Local Attention with Multi-ScaleWindow Attention.
CoRR, January, 2025
Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism.
Proceedings of the 31st International Conference on Computational Linguistics, 2025
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
A Survey on Vision Transformer.
,
,
,
,
,
,
,
,
,
,
,
,
IEEE Trans. Pattern Anal. Mach. Intell., 2023
FDViT: Improve the Hierarchical Architecture of Vision Transformer.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Towards closing the data gap: A project-driven distributed energy resource dataset for the U.S. Grid.
Proceedings of the Companion Proceedings of the 14th ACM International Conference on Future Energy Systems, 2023
Neural architecture tuning with policy adaptation.
Neurocomputing, 2022
A 2030 United States Macro Grid Unlocking Geographical Diversity to Accomplish Clean Energy Goals.
CoRR, 2022
How Much Demand Flexibility Could Have Spared Texas from the 2021 Outage?
CoRR, 2022
BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Federated Learning with Positive and Unlabeled Data.
Proceedings of the International Conference on Machine Learning, 2022
Source-Free Domain Adaptation via Distribution Estimation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Learning Frequency Domain Approximation for Binary Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
ReNAS: Relativistic Evaluation of Neural Architecture Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Manifold Regularized Dynamic Network Pruning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
A Survey on Visual Transformer.
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
VEGA: Towards an End-to-End Configurable AutoML Pipeline.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
DC-NAS: Divide-and-Conquer Neural Architecture Search.
CoRR, 2020
Kernel Based Progressive Distillation for Adder Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
SCOP: Scientific Control for Reliable Neural Network Pruning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Training Binary Neural Networks through Learning with Noisy Supervision.
Proceedings of the 37th International Conference on Machine Learning, 2020
A Semi-Supervised Assessor of Neural Architectures.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
RNAS: Architecture Ranking for Powerful Networks.
CoRR, 2019
Full-Stack Filters to Build Minimum Viable CNNs.
CoRR, 2019
Positive-Unlabeled Compression on the Cloud.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Multi-Positive and Unlabeled Learning.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017
Power System Reliability Impact of Energy Storage Integration With Intelligent Operation Strategy.
IEEE Trans. Smart Grid, 2014