6 papers
SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training
Yunjie Pan, Yongyi Yang, Hanmei Yang +1
Training large language models (LLMs) efficiently while preserving model quality poses significant challenges, particularly with subbyte precision supported by state-of-the-art GPU…
Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
Han Yang, Shaofeng Li, Tian Dong +3
Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only po…
AutoNeural: Co-Designing Vision-Language Models for NPU Inference
Wei Chen, Liangmin Wu, Yunhai Hu +9
While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrat…
Adaptive Distribution-aware Quantization for Mixed-Precision Neural Networks
Shaohang Jia, Zhiyong Huang, Zhi Yu +3
Quantization-Aware Training (QAT) is a critical technique for deploying deep neural networks on resource-constrained devices. However, existing methods often face two major challen…
Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
Han Yang, Jian Lan, Yihong Liu +2
Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance…
Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
Lu Chen, Han Yang, Hu Wang +3
Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigat…