6 papers
OpenTWBench (Open Taiwan Benchmark): Taiwan-Domain Knowledge Evaluation for Large Language Models, and How the Measurement Apparatus Shapes the Score
Liang-Hsun Huang, Min-Yi Chen, Chao-Chun Chuang +3
We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench contains 255,854 four-option quest…
What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
Yuanbo Xie, Wenlei Zhu, Tianyun Liu +5
Modern agentic systems fundamentally reshape the security boundary of LLMs by introducing persistent system state including memories, filesystems, tools, and other long-lived conte…
Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation
Yilong Chen, Naibin Gu, Junyuan Shang +8
Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this,…
ExpSeek: Self-Triggered Experience Seeking for Web Agents
Wenyuan Zhang, Xinghua Zhang, Haiyang Yu +5
Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experience…
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
Juwei Yue, Haikuo Li, Jiawei Sheng +4
Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelate…
Graph Wave Networks
Juwei Yue, Haikuo Li, Jiawei Sheng +5
Dynamics modeling has been introduced as a novel paradigm in message passing (MP) of graph neural networks (GNNs). Existing methods consider MP between nodes as a heat diffusion pr…