Publications (8)
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Huanyao Zhang, Jiepeng Zhou, Runhao Zhao +12
Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to address knowledge-intensive…
NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models
Feng Liang, Weixin Zeng, Runhao Zhao +1
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, temporal reasoning, particularly under comp…
Towards Temporal Knowledge Graph Alignment in the Wild
Runhao Zhao, Weixin Zeng, Wentao Zhang +3
Temporal Knowledge Graph Alignment (TKGA) seeks to identify equivalent entities across heterogeneous temporal knowledge graphs (TKGs) for fusion to improve their completeness. Alth…
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion
Jiaze Song, Runhao Zhao, Minghao Xu +2
The paper introduces a new inductive benchmark (BEELINE‑KGC) and a co‑evolutionary discrete diffusion framework (CoDiffGRN) for inferring gene regulatory networks from single‑cell…
BrowseComp-: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimod…
Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge
Runhao Zhao, Weixin Zeng, Wentao Zhang +4
Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compared to General Knowledge Graphs (GKGs). Existing tasks to enrich DKGs rely primaril…
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
DataFlow Team, Bohan Zeng, Daili Hua +39
World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we…
Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning
Yunxiao Guo, Xinjia Xie, Runhao Zhao +3
Flocking is a very challenging problem in a multi-agent system; traditional flocking methods also require complete knowledge of the environment and a precise model for control. In…