I am Yongheng Zhang, a master’s student (2024-2027) at the School of Computer Science and Engineering, Central South University (CSU).

Currently, my research focuses on Large Language Models, Reasoning, and Chain-of-Thought. My research interests are as follows:

• Large Language Model ✈️: Large Language Model Reasoning aims to empower language models with structured and logical thinking beyond pattern matching. By enabling multi-step inference and problem decomposition, it enhances reliability and interpretability, supporting complex decision-making, scientific discovery, and human-level cognition.

• World Model 🌏: The goal of World Models for Video Understanding and Generation is to build agents that perceive, reason, and predict through dynamic visual experiences. By learning structured video representations, they enable accurate understanding, long-term prediction, and creative generation, paving the way for intelligent interaction and simulation of real-world dynamics.

If you are interested in my research, feel free to contact me:

Email: zyhbrz     Wechat: NHistory

🔥 News

📷 Research Experience

• Tencent, Beijing, China
• Research Intern
• 2025.09 - Present

📝 Publications

• ACM MM 2025 (Oral) ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
  Yongheng Zhang*, Xu Liu*, Ruihan Tao, Qiguang Chen, Hao Fei, Wanxiang Che, Libo Qin.

• ACL 2025 (Main) CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models
  Yongheng Zhang*, Xu Liu*, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, Libo Qin.

• AAAI 2026 Let’s Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework
  Yongheng Zhang*, Xu Liu*, Qiguang Chen, Yao Li, Sheng Wang, Libo Qin.

• ACL 2024 (Findings) AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought
  Yongheng Zhang*, Qiguang Chen*, Min Li, Wanxiang Che, Libo Qin.

• EMNLP 2024 (Findings) Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
  Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin.

• ICASSP 2024 LabCLIP: Label-Enhanced Clip for Improving Zero-Shot Text Classification
  Yongheng Zhang, Peng Wang, Qiguang Chen, Jingxuan Zhou, Yongmei Wang, Min Li, Libo Qin.

• ICME 2025 (Oral) MDCoT: Medical Diagnosis Chain-of-Thought with Self-Diagnostic Refinement for Alzheimer’s Disease
  Chunlin Lu*, Yongheng Zhang*, Peng Wang*, Wenpeng Lu, Libo Qin.

• BIBM 2025 (Oral) LAMA-AD: Label-Aware Multi-Agent Alzheimer’s Disease Diagnosis with Counterfactual Reasoning
  Chunlin Lu*, Yongheng Zhang*, Yao Li, Sheng Wang, Libo Qin.

• ToMM 2024 S3 Agent: Unlocking the Power of VLLM for Zero-Shot Multi-modal Sarcasm Detection
  Peng Wang, Yongheng Zhang, Hao Fei, Qiguang Chen, Yukai Wang, Jiasheng Si, Wenpeng Lu, Min Li, Libo Qin.

• NLPCC 2025 (Best Poster Award) MvDDI: A Multi-view Interaction Framework for Few-shot Drug-Drug Interaction
  Zihao Mao, Qiguang Chen, Yongheng Zhang, Ruoxi Zhou, Peng Wang, Yao Li, Sheng Wang, Libo Qin

• FCS 2025 Large Language Models Meet NLP: A Survey
  Libo Qin, Qiguang Chen, Xiachong Feng, Yang Wu, Yongheng Zhang, Yinghui Li, Min Li, Wanxiang Che, Philip S Yu.

📖 Selected Publications

ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models

Yongheng Zhang*, Xu Liu*, Ruihan Tao, Qiguang Chen, Hao Fei, Wanxiang Che, Libo Qin.

(ACM MM 2025, CCF Rank A)

Paper

Code

CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models

Yongheng Zhang*, Xu Liu*, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, Libo Qin.

(ACL 2025, CCF Rank A)

Paper

Code

AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought

Yongheng Zhang*, Qiguang Chen*, Min Li, Wanxiang Che, Libo Qin.

(ACL 2024 Findings, CCF Rank A Findings)

Paper

Code

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin.

(EMNLP 2024 Findings, CCF Rank B Findings)

Paper

Code

🎖 Honors and Awards

• 2025 National Scholarship, China, TOP 0.2%.

• 2025 First-Class Academic Scholarship, Ranking TOP 1.

• 2024 NLPCC 2024, Coreference Resolution and Relation Extraction Task, Second Runner-Up.

• 2023 China National University Student Innovation & Entrepreneurship Development Program.

• 2022 Chinese Collegiate Computing Competition, National First Prize.

🚀 Open Source Projects

• MLNLP Github LLMs-from-scratch-CN .

• MLNLP Github Academic-Resume-Template .

🌍 Community Service

• PC Member / Reviewer: NeurIPS, ACL ARR, AAAI, EMNLP ARR, NAACL ARR, ICASSP, ICME, NLPCC.

• MLNLP Community Secretary.

🙌 If you like this homepage template, welcome to star and fork the open-sourced template AcadHomepage.