7 papers
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
Yinyi Luo, Yiqiao Jin, Weichen Yu +6
While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational co…
Classroom AI: Large Language Models as Grade-Specific Teachers
Jio Oh, Steven Euijong Whang, James Evans +1
Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds of millions of children, but th…
Temporal Pair Consistency for Variance-Reduced Flow Matching
Chika Maduabuchi, Jindong Wang
Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that tr…
Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents
Jiatong Li, Changdae Oh, Hyeong Kyu Choi +2
User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stateful environment. In such intera…
FedUMM: A General Framework for Federated Learning with Unified Multimodal Models
Zhaolong Su, Leheng Zhao, Xiaoying Wu +2
Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically…
Topology-aware Neural Flux Prediction Guided by Physics
Haoyang Jiang, Jindong Wang, Xingquan Zhu +1
Graph Neural Networks (GNNs) often struggle in preserving high-frequency components of nodal signals when dealing with directed graphs. Such components are crucial for modeling flo…