180 citations
- The University of MelbourneAU7 papers
- Harbin Institute of TechnologyCN6 papers
- Chinese Academy of SciencesCN3 papers
- Shanghai Jiao Tong UniversityCN3 papers
- University of Louisiana at LafayetteUS3 papers
- Alibaba Group (China)CN2 papers
- Chinese University of Hong KongHK2 papers
- Department of SpaceIN2 papers
- Hefei University of TechnologyCN2 papers
- Huawei Technologies (China)CN2 papers
- Huawei Technologies (United Kingdom)GB2 papers
- Huawei Technologies (United States)US2 papers
53 papers
Crowding controls the scaling of bus frequency with demand
Siddharth Patwardhan, Şirag Erkol, Filippo Radicchi +1
Cities must allocate limited resources to maintain mobility, with uncertainties about the resulting state of the system. Analyzing roughly 3,000 bus routes with more than 4 billion…
Cross-Stack Validation of Language-Model Training: A Clinical Fine-Tuning Case Study
Thang Tran, Lan Dang
Neural network training has an oracle problem: a run can converge normally and yield a usable model while the software beneath it computes something other than specified. Almost al…
Vorticity Dissipation Based Routing: A Fluid-Kinetic Framework for Loop-Free Transport in Ultra-Dense Networks
Wen-Yu Dong, Weiwei Jiang, Song Zhao +3
Discrete routing protocols in ultra-dense wireless networks are constrained by signaling overhead and transient routing loops that degrade radio-resource efficiency. While continuu…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
Bo Deng, Kang Zhou, Lifan Guo +6
Agents used over time encounter recurring professional work: each case requires different evidence and judgment, while the underlying workflow can be reused. Benchmarks built from…
Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
Wenjuan Li, Yitao Liu, Runze Chen +1
Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable comp…
DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent Systems
Axel Dunkel
The Model Context Protocol (MCP) is the standard interface between large language model (LLM) agents and external tools. At organizational scale, however, it exposes two structural…