6 papers
CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou +8
Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual r…
GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models
Ziyang Wang, Jiangfeng Xiao, Chuan Xiao +3
Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune…
Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
Rei Taniguchi, Yuyang Dong, Makoto Onizuka +1
Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been propo…
ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework
Yusong Wang, Chuang Yang, Jiawei Wang +5
Human mobility generation aims to synthesize plausible trajectory data, which is widely used in urban system research. While Large Language Model-based methods excel at generating…
Serving Large Language Models on Huawei CloudMatrix384
Pengfei Zuo, Huimin Lin, Junbo Deng +43
The rapid evolution of large language models (LLMs), driven by growing parameter scales, adoption of mixture-of-experts (MoE) architectures, and expanding context lengths, imposes…
SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity
Chuang Yang, Renhe Jiang, Xiaohang Xu +2
Free-space trajectory similarity calculation, e.g., DTW, Hausdorff, and Frechet, often incur quadratic time complexity, thus learning-based methods have been proposed to accelerate…