4 papers
SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance
Pengyiang Liu, Zhongyue Shi, Hongye Hao +7
Video understanding requires models to continuously track and update world state during playback. Although existing benchmarks have advanced video understanding evaluation across m…
RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization
Siwei Zhang, Yun Xiong, Xi Chen +4
Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks vi…
Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
Siwei Zhang, Yun Xiong, Yateng Tang +6
Temporal graph neural networks (TGNNs) have shown remarkable performance in temporal graph modeling. However, real-world temporal graphs often possess rich textual information, giv…
Rethinking Time Encoding via Learnable Transformation Functions
Xi Chen, Yateng Tang, Jiarong Xu +5
Effectively modeling time information and incorporating it into applications or models involving chronologically occurring events is crucial. Real-world scenarios often involve div…