7 papers
Spike-Aware C++ INT8 Inference for Sparse Spiking Language Models on Commodity CPUs
Ting Liu
Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit. This paper studies that property from a systems perspective. Building on…
SymbolicLight V1: Spike-Gated Dual-Path Language Modeling at High Activation Sparsity
Ting Liu
Natively trained spiking language models must preserve information across time while operating through sparse binary activations, a combination that has produced a persistent quali…
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
Shangzhan Li, Xinyu Yin, Xuanyu Jin +8
Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resor…
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
Yilong Chen, Yanxi Xie, Zitian Gao +10
Large token-indexed lookup tables provide a compute-decoupled scaling path, but their practical gains are often limited by poor parameter efficiency and rapid memory growth. We att…
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
Jiali Wei, Ming Fan, Guoheng Sun +3
The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasib…
AEGIS : Automated Co-Evolutionary Framework for Guarding Prompt Injections Schema
Ting-Chun Liu, Ching-Yu Hsu, Kuan-Yi Lee +2
Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a light…