👋 Hi! I am Yiyun Zhou (周逸云 in Chinese), a third-year master’s student in Zhejiang University and advised by Prof. Jingyuan Chen.

🔬 My research has centered on the data miming, multimodal learning, LLM, multi-view multi-label learning, and AIGC (video generation and image editing). I have published some papers on the above topics at the top-tier international AI conferences such as KDD, WWW, ACL, AAAI and ECML-PKDD. Recently, I devote myself to AIGC (video generation and image editing).

I will graduate in 2026 and am currently seeking PhD opportunities for fall admission. Feel free to contact me at yiyunzhou@zju.edu.cn.

📢 News

• 2025/11/08 [AAAI’26] TLV-CoRe, a CLIP-based tactile-language-vision collaborative representation learning framework that integrates sensor-aware modulation, tactile-irrelevant decoupled learning, and a unified bridging adapter for tri-modal alignment, got accepted for AAAI 2026!
• 2025/11/08 [AAAI’26] AccKV, an adaptive-focusing and cross-calibration framework for efficient audio-video large language model inference that integrates attention redistribution, layer-wise modality prioritization, and cross-modal KV alignment, got accepted for AAAI 2026!
• 2025/09/18 [NeurIPS’25 (Spotlight)] TDLSR, a theory-driven framework for incomplete multi-view multi-label learning that integrates proximity-aware graph attention recovery, mutual-information-based representation disentanglement, and label-specific semantic modeling, got accepted for NeurIPS 2025!
• 2025/07/06 [ACMMM’25] IP-FVR, a novel method for identity-prompted face video restoration leveraging reference-guided cross-attention and feedback-based identity stabilization, got accepted for ACMMM 2025!
• 2025/05/27 [ECML-PKDD’25 (Oral)] DKT2, a applicable and comprehensive deep knowledge tracing model that integrates Rasch-model-based input processing and IRT-based output interpretation with xLSTM for improved knowledge state modeling, got accepted for ECML-PKDD 2025! Code has been available!
• 2025/05/15 [ACL’25] CoLA, a flexible and collaborative LoRA architecture with enhanced initialization and multiple collaboration strategies to improve parameter-efficient fine-tuning under data scarcity, got accepted for ACL 2025! Code has been available!
• 2025/05/14 [KDD’25 (Oral)] Cuff-KT, a controllable, tuning-free, fast and flexible knowledge tracing framework that adapts to real-time shifts in learner behavior by dynamically generating model parameters without fine-tuning, got accepted for SIGKDD 2025! Code has been available!
• 2025/04/29 [IJCAI’25] TransKT, a contrastive cross-course knowledge tracing model that constructs a concept graph using LLM-generated semantics and transfers knowledge across courses via GCNs and cross-course contrastive learning, got accepted for IJCAI 2025!
• 2025/01/20 [WWW’25] DisKT, an approximate causal knowledge tracing model that disentangles student abilities and eliminates cognitive bias by modeling confounders under the premise of shielding contradictory behavior, got accepted for WWW 2025! Code has been available!

📝 Publications

AAAI 2026

Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities

Yiyun Zhou, Mingjing Xu, Jingwei Shi, Quanjiang Li, Jingyuan Chen

KDD 2025 (Oral)

Cuff-KT: Tackling Learners’ Real-time Learning Pattern Adjustment via Tuning-Free Knowledge State Guided Model Updating

Yiyun Zhou, Zheqi Lv, Shengyu Zhang, Jingyuan Chen

ACL 2025

CoLA: Collaborative Low-Rank Adaptation

Yiyun Zhou, Chang Yao, Jingyuan Chen

WWW 2025

DisKT: Disentangled Knowledge Tracing for Alleviating Cognitive Bias

Yiyun Zhou, Zheqi Lv, Shengyu Zhang, Jingyuan Chen

ECML-PKDD 2025 (Oral)

DKT2: Revisiting Applicable and Comprehensive Knowledge Tracing in Large-Scale Data

Yiyun Zhou, Wenkang Han, Jingyuan Chen

Zhonghua Jiang, Kui Chen, Kunxi Li, Keting Yin, Yiyun Zhou, Zhaode Wang, Chengfei Lv, Shengyu Zhang, "AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization". [openreview]

Quanjiang Li, Tianxiang Xu, Tingjin Luo, Yan Zhong, Yang Li, Yiyun Zhou, Chenping Hou, "Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning". [openreview]

Wenkang Han, Wang Lin, Yiyun Zhou, Qi Liu, Shulei Wang, Chang Yao, Jingyuan Chen, "Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration". [arXiv]

Wenkang Han, Wang Lin, Liya Hu, Zhenlong Dai, Yiyun Zhou, Mengze Li, Zemin Liu, Chang Yao, Jingyuan Chen, "Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer". [arXiv]

🎖 Honors and Awards

• 2025.10 National Scholarship of China (master) (Top 1%, 2/327)

• 2019-2023 One-class Scholarship of Nanchang University

• 2019-2023 Social Activist, Model Student, and Model Student Exemplar

• 2019-2023 CCPC/ICPC Asia Regional Contest and Invitational Contest, 🥉Bronze Medal🥉 and 🥈Silver Medal🥈

• 2019-2023 Jiangxi Province Collegiate Programming Contest, 🥈2nd Place🥈

🧑‍🎨 Professional Services

PC Member of Conferences:

• Program Committee Member of AAAI (2026)
• Program Committee Member of ICLR (2026)
• Program Committee Member of CVPR (2026)

Invited Reviewer of Journals:

• Invited Reviewer for ACM Transactions on Information Systems (TOIS)

📖 Educations

• 2023.09 - 2026.03, Master, Software Engineering, Zhejiang University.

• 2019.09 - 2023.06, Undergraduate, Computer Science and Technology, Nanchang Univeristy.