5 papers
Achieving Sparse Activation in Small Language Models
Jifeng Song, Kai Huang, Xiangyu Yin +2
Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLM…
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing
Kai Huang, Haoming Wang, Wei Gao
Text-to-image diffusion models can be fine-tuned in custom domains to adapt to specific user preferences, but such adaptability has also been utilized for illegal purposes, such as…
Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
Kai Huang, Wei Gao
With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving h…
ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
Kai Huang, Boyuan Yang, Wei Gao
On-device training is essential for neural networks (NNs) to continuously adapt to new online data, but can be time-consuming due to the device's limited computing power. To speed…
Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI
Kai Huang, Boyuan Yang, Wei Gao
Large Language Models (LLMs) are capable of reasoning over diverse input data modalities through pre-trained encoders. However, the growing diversity of input data modalities preve…