Publications (7)
Improving Auto-Augment via Augmentation-Wise Weight Sharing
Keyu Tian, Chen Lin, Ming Sun +3
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search i…
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Keyu Tian, Yi Jiang, Zehuan Yuan +2
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-r…
Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training
Man Yao, Xuerui Qiu, Tianxiang Hu +7
The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major c…
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket
Zhaokun Zhou, Kaiwei Che, Wei Fang +5
Spiking Neural Networks (SNNs), known for their biologically plausible architecture, face the challenge of limited performance. The self-attention mechanism, which is the cornersto…
CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models
Ryan Feng Lin, Keyu Tian, Hanming Zheng +3
The emergence of large language models (LLMs) has sparked much interest in creating LLM-based digital populations that can be applied to many applications such as social simulation…
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
Keyu Tian, Yi Jiang, Qishuai Diao +3
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution…
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Ronghao Guo, Chen Lin, Chuming Li +4
One-shot NAS method has attracted much interest from the research community due to its remarkable training efficiency and capacity to discover high performance models. However, the…