7 papers
MSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information
Xinyu Chen, Liangjian Wen, Jiang Duan +7
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions. Balance-oriented method…
Pay More Attention To Text In High-Resolution MLLMs
Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu +7
Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or su…
PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting
Ao Hu, Liangjian Wen, Jiang Duan +7
Long-term time series forecasting (LTSF) plays a crucial role in fields such as energy management, finance, and traffic prediction. Transformer-based models have adopted patch-base…
AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models
Faqiang Qian, Kang An, Weikun Zhang +6
Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable…
Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents
Yuhan Guo, Cong Guo, Aiwen Sun +12
Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In t…
TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting
Ao Hu, Dongkai Wang, Yong Dai +7
Time series forecasting is extensively applied across diverse domains. Transformer-based models demonstrate significant potential in modeling cross-time and cross-variable interact…
GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning
Jun Wang, Hao Ruan, Liangjian Wen +2
Visual gaze estimation, with its wide-ranging application scenarios, has garnered increasing attention within the research community. Although existing approaches infer gaze solely…