Yawen Zeng
|
|
Biography
Hello, thanks for stopping by! I am a casual player focusing on Large Vision Language Models, General Agents, and Multi-Modal Applications. Due to my adventures in studying, interning, and working, I have collaborated with various institutions, including Hunan University, South China University of Technology, Tencent, and ByteDance, etc. I have had the privilege of publishing my research in esteemed academic conferences such as CVPR, ICCV, AAAI, WWW, SIGIR, ICLR, TNNLS, and TMM.
News
- (2025-08) Our paper is accepted as EMNLP 2025 findings.
- (2025-07) We won the ACM MM 2025 Grand Challenge (Rank 1stđ ).
- (2025-07) Two papers are accecpted by ACM MM 2025.
- (2025-06) Our work is accecpted by ICCV 2025.
- (2025-04) Our work is accecpted by SIGIR 2025 as an Oral paper.
- (2025-01) Two papers are accecpted by WWW 2025 as Oral papers.
- (2025-01) One paper is accecpted by ICLR 2025.
more news
- (2024-01) One paper is accecpted by WWW 2024.
- (2024-01) One paper is accecpted by ICLR 2024.
- (2023-12) Our work is accecpted by AAAI 2024.
- (2023-08) Our work is accecpted by TMM 2023.
- (2023-04) Our work is accecpted by SIGIR 2023.
- (2023-02) I am awarded Excellent New Employee in ByteDance AI Lab.
- (2022-11) Our work is accecpted by AAAI 2023.
- (2022-10) Our work is accecpted by EMNLP 2022 as an Oral paper.
- (2022-04) Two papers are accecpted by ICMR 2022 as Oral papers.
- (2022-04) Our work is accecpted by TNNLS 2022.
- (2022-04) Our work is accecpted by SIGIR 2022.
- (2021-07) One paper is accecpted by ACM MM 2021 as an Oral paper.
- (2021-03) Our work is accecpted by CVPR 2021.
- (2020-10) I am awarded National Scholarship for Postgraduate.
- (2020-07) Two papers are accecpted by ACM MM 2020, one of which is an Oral paper.
Selected Publications
| QuantAgents: Towards Multi-agent Financial System via Simulated Trading |
| Xiangyu Li*, Yawen Zeng*, Xiaofen Xing, Jin Xu, Xiangmin Xu |
| EMNLP, 2025 |
| MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions |
| Zeyu Huang, Juyuan Wang, Longfeng Chen, Boyi Xiao, Leng Cai, Yawen Zengâ¨, Jin Xu⨠|
| ACM MM, 2025 |
| Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation |
| Shouxing Ma, Yawen Zeng, Shiqing Wu, Guandong Xu |
| ACM MM, 2025 |
| COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets |
| Lingyu Chen*, Yawen Zeng*, Yue Wang, Peng Wan, Guo-chen Ning, Hongen Liao, Daoqiang Zhang, Fang Chen |
| ICCV, 2025 |
| IVCR-200K: A Large-Scale Multi-Turn Dialogue Benchmark for Interactive Video Corpus Retrieval |
| Ning Han*, Yawen Zeng*, Shaohua Long, Chengqing Li, Sijie Yang, Dun Tan, Jianfeng Dong, Jingjing Chen |
| SIGIR, 2025 |
| DataMan: Data Manager for Pre-training Large Language Models |
| Ru Peng, Kexin Yang, Yawen Zeng, Junyang Lin, Dayiheng Liu, Junbo Zhao |
| ICLR, 2025 |
| HedgeAgents: A Balanced-aware Multi-agent Financial Trading System |
| Xiangyu Li*, Yawen Zeng*, Xiaofen Xing, Jin Xu, Xiangmin Xu |
| WWW, 2025 |
| RTBAgent: A LLM-based Agent System for Real-Time Bidding |
| Leng Cai, Junxuan He, Yikai Li, Junjie Liang, Yuanping Lin, Ziming Quan, Yawen Zengâ¨, Jin Xu⨠|
| WWW, 2025 |
| Energy-based Automated Model Evaluation |
| Ru Peng, Heming Zou, Haobo Wang, Yawen Zeng, Zenan Huang, Junbo Zhao |
| ICLR, 2024 |
| FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model |
| Xiangyu Li, Xinjie Shen, Yawen Zeng, Xiaofen Xing, Jin Xu |
| WWW, 2024 |
| Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification |
| Yajing Zhai*, Yawen Zeng*, Zhiyong Huang, Zheng Qin, Xin Jin, Da Cao |
| AAAI, 2024 |
| VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool |
| Yan Wang, Yawen Zengâ¨, Jingsheng Zheng, Xiaofen Xing, Jin Xu, Xiangmin Xu |
| ACL, 2024 (workshop) |
| HindRec: Aligning User Preferences for Recommendation via Hindsight Fine-tuning |
| Yawen Zeng*, Huanwen Wang*, Lingyu Chen, Wenshu Chen, Ran Chen, Hao Chen |
| KDD, 2024 (workshop) |
| RetrievalMMT: Retrieval-Constrained Multi-Modal Prompt Learning for Multi-Modal Machine Translation |
| Yan Wang*, Yawen Zeng*, Junjie Liang, Xiaofen Xing, Jin Xu, Xiangmin Xu |
| ICMR, 2024 |
| Temporally Language Grounding with Multi-modal Multi-Prompt Tuning |
| Yawen Zeng, Ning Han, Keyu Pan, Qin Jin |
| TMM, 2023 |
| Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models |
| Keyu Pan, Yawen Zeng |
| arXiv preprint, 2023 |
| RewardTLG: Learning to Temporally Language Grounding from Flexible Reward |
| Yawen Zeng, Keyu Pan, Ning Han |
| SIGIR, 2023 |
| Multi-Modal Knowledge Hypergraph for Diverse Image Retrieval |
| Yawen Zeng, Qin Jin, Tengfei Bao, Wenfeng Li |
| AAAI, 2023 |
| Contrastive Topic-enhanced Network for Video Captioning |
| Yawen Zeng, Yiru Wang, Dongliang Liao, Gongfu Li, Jin Xu, Bo Liu, Xiangmin Xu, Hong Man |
| ESWA, 2023 |
| BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval |
| Ning Han, Yawen Zeng, Chuhao Shi, Guangyi Xiao, Hao Chen, Jingjing Chen |
| TOMM, 2023 |
| Better Sign Language Translation with Monolingual Data |
| Ru Peng, Yawen Zeng, Junbo Zhao |
| arXiv preprint, 2023 |
| Keyword-Based Diverse Image Retrieval with Variational Multiple Instance Graph |
| Yawen Zeng, Yiru Wang, Dongliang Liao, Gongfu Li, Weijie Huang, Jin Xu, Da Cao, Hong Man |
| TNNLS, 2022 |
| Point Prompt Tuning for Temporally Language Grounding |
| Yawen Zeng |
| SIGIR, 2022 |
| Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation |
| Ru Peng*, Yawen Zeng*, Junbo Zhao |
| EMNLP, 2022 |
| HybridVocab: Towards Multi-Modal Machine Translation via Multi-Aspect Alignment |
| Ru Peng*, Yawen Zeng*, Junbo Zhao |
| ICMR, 2022 |
| TriReID: Towards Multi-Modal Person Re-Identification via Descriptive Fusion Model |
| Yajing Zhai*, Yawen Zeng*, Da Cao, Shaofei Lu |
| ICMR, 2022 |
| Fine-grained cross-modal alignment network for text-video retrieval |
| Ning Han, Jingjing Chen, Guangyi Xiao, Hao Zhang, Yawen Zeng, Hao Chen |
| ACM MM, 2021 |
| Moment is Important: Language-Based Video Moment Retrieval via Adversarial Learning |
| Yawen Zeng, Da Cao, Hanling Zhang, Jiao Xu, Zheng Qin |
| TOMM, 2021 |
| Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval |
| Yawen Zeng, Da Cao, Xiaochi Wei, Meng Liu, Zhou Zhao, Zheng Qin |
| CVPR, 2021 |
| Adversarial Video Moment Retrieval by Jointly Modeling Ranking and Localization |
| Da Cao, Yawen Zeng, Xiaochi Wei, Liqiang Nie, Richang Hong, Zheng Qin |
| ACM MM, 2020 |
| STRONG: Spatio-Temporal Reinforcement Learning for Cross-Modal Video Moment Localizationn |
| Da Cao, Yawen Zeng, Meng Liu, Xiangnan He, Meng Wang, Zheng Qin |
| ACM MM, 2020 |
Awards
| HEAR: A Holistic Extraction and Agentic Reasoning Framework for Document Understanding |
| Longfeng Chen, Zheng Xiao, Juyuan Wang, Zeyu Huang, Yawen Zengâ¨, Jin Xu⨠|
| ACM Multimedia 2025 Grand Challenge (Rank 1stđ ) |
| SYSUpporter Team at BEA 2025 Shared Task: Class Compensation and Assignment Optimization for LLM-generated Tutor Identification |
| Longfeng Chen, Zeyu Huang, Zheng Xiao, Yawen Zengâ¨, Jin Xu⨠|
| ACL 2025 BEA Shared Task (Rank 2ndđĽ) |
Academic Service
| Conference Reviewer for CVPR, ICCV, ECCV, ACL, EMNLP, KDD, WWW, NeurIPS, AAAI. |
| Journal Reviewer for TPAMI, TNNLS, TMM, TKDE, TKDD, TOMM. |