Publications (7)
Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework
Zhen Tao, Zhiyu Li, Runyu Chen +2
Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. However, their widespread use raises conce…
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
Yihan Wang, Peiyu Liu, Runyu Chen +1
Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflo…
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
Kairun Wen, Yuzhi Huang, Runyu Chen +16
Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent…
Energy Transport in Randomly Coupled Quantum Systems: A Perturbative Approach
Tingfei Li, Runyu Chen
We study energy transport between two quantum systems coupled through a random interaction. The central feature of our approach is to model the coupling as a Gaussian random matrix…
CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
Ruiqi Wang, Ruikang Liu, Runyu Chen +4
Detecting anomalies in tabular data is critical for many real-world applications, such as credit card fraud detection. With the rapid advancements in large language models (LLMs),…
Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks
Yihan Wang, Peiyu Liu, Runyu Chen +2
Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challengin…
LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams
Yongxuan Wu, Runyu Chen, Peiyu Liu +1
Long-context understanding poses significant challenges in natural language processing, particularly for real-world dialogues characterized by speech-based elements, high redundanc…