数智融合创新研究团队 Since 2021

Digital & Intelligence Convergence Team (DICT)

我们聚焦于模型驱动的软硬件智能系统，致力于构建从数据到模型、再到系统落地的统一方法论。团队围绕智能模型与计算架构的深度协同，探索高效、可解释且可部署的智能系统，在感知、决策与系统优化等关键环节实现从算法到系统的跨层融合。

We focus on model-driven intelligent systems across hardware and software, aiming to establish unified methodologies from data and models to real-world deployment. Our research emphasizes the co-design of intelligent models and computing architectures, enabling efficient, interpretable, and deployable systems for perception, decision-making, and system-level optimization.

主要研究方向 Research Focus

Latest News

  • 2026-03: 📄 (Main) Paper accepted at Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) — “Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation”, Liu, Jinliang (到湖本科实习生), Bai, Jiale, 🔥 Zeng Shaoning
  • 2026-03: 📄 (Findings) Paper accepted at Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) — “A Dual-Phase Self-Evolution Framework for Large Language Models”, Sun, Haoran (到湖本科实习生), Zhang, Zekun, 🔥 Zeng Shaoning
  • 2026-03: 📄 (Findings) Paper accepted at Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) — “Preference-Aware Memory Update for Long-Term LLM Agents”, Sun, Haoran (到湖本科实习生), Zhang, Zekun, 🔥 Zeng Shaoning
  • 2025-12: 📄 Paper accepted at AAAI — “SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining”, Wang, Jiayu, Bian, Haoyu (到湖本科实习生), Sun, Haoran, 🔥 Zeng Shaoning

  • Self-Evolving AI Agent System
    From data to intelligent agents with continuous learning
    Learn More →

  • Autonomous Robot Perception System
    Robust multi-modal perception and navigation
    Learn More →

Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
Liu, Jinliang, Bai, Jiale, 🔥 Zeng Shaoning
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) 2026

A Dual-Phase Self-Evolution Framework for Large Language Models
Sun, Haoran, Zhang, Zekun, 🔥 Zeng Shaoning
Findings of the Association for Computational Linguistics: ACL 2026 2026

Preference-Aware Memory Update for Long-Term LLM Agents
Sun, Haoran, Zhang, Zekun, 🔥 Zeng Shaoning
Findings of the Association for Computational Linguistics: ACL 2026 2026

SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining
Wang, Jiayu, Bian, Haoyu, Sun, Haoran, 🔥 Zeng Shaoning
AAAI 2026

H-MEM: Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
Sun, Haoran, 🔥 Zeng Shaoning, Zhang, Bob
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) 2026

👉 View All Publications →

Contact

数智融合创新研究团队，2021-至今 电子科技大学长三角研究院（湖州） DICT of YDRI (Huzhou), UESTC

校企合作、到湖实习（本科生、研究生）及学术交流等， 请联系 Email: zsn (AT) outlook.com