Dayuan Fu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dayuan Fu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Chen Zeng
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Chenyang He
Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China
1 shared publication - Daichi Guo
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Gang Zhao
Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Guanting Dong
Renmin University of China, Beijing, China
1 shared publication - Jiadi Su
Fudan University, Shanghai, Shanghai, China and Fudan University, Shanghai, Shanghai, China
1 shared publication
Latest Publications
- 2 June 2026
- Published by Elsevier in Neurocomputing
- Vol. 697
Fine-grained inter-series dependency enhanced mining for multi-domain multivariate time series forecasts
- 2 June 2026
- Published by Elsevier in Neurocomputing
- Vol. 697
Fine-grained inter-series dependency enhanced mining for multi-domain multivariate time series forecasts
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Interaction as Intelligence: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration
As AI systems engage in extended thinking processes for research tasks, interaction becomes increasingly important for effective long-horizon research. In these tasks, many current deep research systems still follow an “input–wait–output” paradigm: users submit a query and receive results only after a non-interruptible process with limited visibility into intermediate decisions. In multi-agent systems, delayed feedback can amplify early errors, limit query refinement during investigation and reduce opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a multi-agent deep research system that enables users to monitor and steer an ongoing research process through targeted interventions during execution. Deep Cognition provides two key capabilities: (1) Transparent, controllable, and interruptible interaction that reveals AI reasoning, exposing intermediate plans and evidence and allowing users to intervene at intermediate checkpoints; (2) Fine-grained bidirectional dialogue that enables per-subagent control during execution.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessInteraction as Intelligence: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration
As AI systems engage in extended thinking processes for research tasks, interaction becomes increasingly important for effective long-horizon research. In these tasks, many current deep research systems still follow an “input–wait–output” paradigm: users submit a query and receive results only after a non-interruptible process with limited visibility into intermediate decisions. In multi-agent systems, delayed feedback can amplify early errors, limit query refinement during investigation and reduce opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a multi-agent deep research system that enables users to monitor and steer an ongoing research process through targeted interventions during execution. Deep Cognition provides two key capabilities: (1) Transparent, controllable, and interruptible interaction that reveals AI reasoning, exposing intermediate plans and evidence and allowing users to intervene at intermediate checkpoints; (2) Fine-grained bidirectional dialogue that enables per-subagent control during execution.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 430-440
A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 430-440
Open AccessA Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
The objective of few-shot named entity recognition is to identify named entities with limited labeled instances. Previous works have primarily focused on optimizing the traditional token-wise classification framework, while neglecting the exploration of information based on NER data characteristics. To address this issue, we propose a Multi-Task Semantic Decomposition Framework via Joint Task-specific Pre-training (MSDP) for few-shot NER. Drawing inspiration from demonstration-based and contrastive learning, we introduce two novel pre-training tasks: Demonstration-based Masked Language Modeling (MLM) and Class Contrastive Discrimination. These tasks effectively incorporate entity boundary information and enhance entity representation in Pre-trained Language Models (PLMs). In the downstream main task, we introduce a multi-task joint optimization framework with the semantic decomposing method, which facilitates the model to integrate two different semantic information for entity classification. Experimental results of two few-shot NER benchmarks demonstrate that MSDP consistently outperforms strong baselines by a large margin. Extensive analyses validate the effectiveness and generalization of MSDP.