Yanqi Dai

13 papers A* 2A 1Journal 7Unranked 3
YearRankTypeTitle / Venue / Authors
2026 A* conf
Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty.
WWW
Yanqi Dai, Yong Wang, Zebin You, Dong Jing, Xiangxiang Chu, Zhiwu Lu
2026 J jnl
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation.
CoRR
Yanqi Dai, Yuxiang Ji, Xiao Zhang, Yong Wang, Xiangxiang Chu, Zhiwu Lu
2026 J jnl
MuSteerNet: Human Reaction Generation from Videos via Observation-Reaction Mutual Steering.
CoRR
Yuan Zhou, Yongzhi Li, Yanqi Dai, Xingyu Zhu, Yi Tan, Qingshan Xu, Beier Zhu, Richang Hong, Hanwang Zhang
2025 — conf
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds.
NAACL (Long Papers)
Lei Wang, Jianxun Lian, Yi Huang, Yanqi Dai, Haoxuan Li, Xu Chen, Xing Xie, Ji-Rong Wen
2025 A* conf
MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents.
ICLR
Yanqi Dai, Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Zhiwu Lu
2024 J jnl
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts.
CoRR
Jinqiang Long, Yanqi Dai, Guoxing Yang, Hongpeng Lin, Nanyi Fei, Yizhao Gao, Zhiwu Lu
2024 J jnl
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds.
CoRR
Lei Wang, Jianxun Lian, Yi Huang, Yanqi Dai, Haoxuan Li, Xu Chen, Xing Xie, Ji-Rong Wen
2024 J jnl
CoTBal: Comprehensive Task Balancing for Multi-Task Visual Instruction Tuning.
CoRR
Yanqi Dai, Dong Jing, Nanyi Fei, Zhiwu Lu
2024 J jnl
MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents.
CoRR
Yanqi Dai, Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Zhiwu Lu
2024 — conf
VEMO: A Versatile Elastic Multi-modal Model for Search-Oriented Multi-task Learning.
ECIR (1)
Nanyi Fei, Hao Jiang, Haoyu Lu, Jinqiang Long, Yanqi Dai, Tuo Fan, Zhao Cao, Zhiwu Lu
2023 A conf
Improvable Gap Balancing for Multi-Task Learning.
UAI
Yanqi Dai, Nanyi Fei, Zhiwu Lu
2023 J jnl
Improvable Gap Balancing for Multi-Task Learning.
CoRR
Yanqi Dai, Nanyi Fei, Zhiwu Lu
2021 — conf
TRGAN: Text to Image Generation Through Optimizing Initial Image.
ICONIP (5)
Liang Zhao, Xinwei Li, Pingda Huang, Zhikui Chen, Yanqi Dai, Tianyu Li