Zhe Xu

Orcid: 0000-0001-6898-3443

Affiliations:
  • Hong Kong University of Science and Technology (HKUST), Hong Kong
  • Xidian University, School of Electronic Engineering, Xian, China (PhD)


According to our database1, Zhe Xu authored at least 20 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems.
ACM Comput. Surv., April, 2026

Attention Basin: Why Contextual Position Matters in Large Language Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Perceive, Reflect and Understand Long Video: Progressive Multi-Granular Clue Exploration with Interactive Agents.
CoRR, September, 2025

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey.
ACM Comput. Surv., August, 2025

MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions.
CoRR, March, 2025

Robust Temporal Action Localization With Meta Boundary Refinement.
IEEE Trans. Multim., 2025

Parameter-efficient weakly supervised referring video object segmentation via chain-of-thought reasoning.
Complex Intell. Syst., 2025

MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Intent-driven In-context Learning for Few-shot Dialogue State Tracking.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Compress to One Point: Neural Collapse for Pre-Trained Model-Based Class-Incremental Learning.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
Class-Incremental Unsupervised Domain Adaptation via Pseudo-Label Distillation.
IEEE Trans. Image Process., 2024

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey.
CoRR, 2024

A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems.
CoRR, 2024

Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons.
CoRR, 2024

Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation.
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024

Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
Bilateral Relation Distillation for Weakly Supervised Temporal Action Localization.
IEEE Trans. Pattern Anal. Mach. Intell., October, 2023

Point-Supervised Video Temporal Grounding.
IEEE Trans. Multim., 2023

2022
HiSA: Hierarchically Semantic Associating for Video Temporal Grounding.
IEEE Trans. Image Process., 2022

2021
Generalized Zero-Shot Learning via Disentangled Representation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021


  Loading...