4 accepted papers
NVIDIA's 2:4 Sparse Tensor Cores deliver $2\times$ throughput but demand 50% pruning—a ratio that collapses LLM reasoning accuracy (Qwen3: 54%→15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive *no* hardware support, falling back to dense execution. We present *…
The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient edge inference for ternary LLMs remain scarce. To bridge this gap, we introduce Bitnet.cpp, an inference system optimiz…
Utilizing Large Language Models (LLMs) for complex tasks is challenging, often involving a time-consuming and uncontrollable prompt engineering process. This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming intera…
Large language models (LLMs) demonstrate impressive multilingual capability, but their performance varies substantially across different languages. In this work, we introduce a simple yet effective method, called cross-lingual-thought prompting (XLT), to systematically improve the multilingual capab…