Human-Computer Interaction

Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari et al.

This work addresses the limitation of auditory AI in aligning with human perception for applications like hearing aids or communication systems, representing a novel paradigm rather than an incremental improvement.

Ailin Huang, Boyong Wu, Bruce Wang et al.

This addresses high costs, weak dynamic control, and limited intelligence in speech interaction models for developers and researchers, representing a significant advancement rather than an incremental improvement.

Sari Masri, Huthaifa I. Ashqar, Mohammed Elhenawy

This proposes a new paradigm for traffic management systems that could improve efficiency at intersections for drivers and autonomous vehicles.

Hamed Rahimi, Adil Bahaj, Mouad Abrini et al.

This work addresses the problem of personalized human-robot interactions for diverse users, providing a significant advancement in social robotics.

Chao Yan, Boyong Wu, Peng Yang et al.

This addresses the need for advanced audio editing tools for content creators and researchers, offering a novel approach that is not incremental.

Runtong Wu, Jiayao Song, Fei Teng et al.

This addresses the dual burden of data analysis and member checking for researchers and participants in narrative inquiry, representing a first attempt in the field.

Jiangrong Shen, Yulin Xie, Qi Xu et al.

This work addresses critical challenges in energy-efficient multimodal sensory processing for neuromorphic systems, establishing a new paradigm rather than being incremental.

Steven-Shine Chen, Jimin Lee, Paul Pu Liang

This work addresses the need for more effective and engaging educational technologies, particularly for students struggling with complex math concepts.

Zhuoyun Du, Lujie Zheng, Renjun Hu et al.

This addresses the problem of scalable and effective medical training for healthcare professionals, representing a novel application of agent coevolution rather than an incremental improvement.

Bufang Yang, Lilin Xu, Liekang Zeng et al.

This work addresses the need for more effective proactive AI assistants in daily scenarios, representing a novel approach rather than an incremental improvement.

Xinye Cao, Hongcan Guo, Guoshun Nan et al.

This addresses efficiency and flexibility challenges for resource-constrained mobile environments in interactive multimodal applications like route planning.

Omar Shaikh, Valentin Teutschbein, Kanishk Gandhi et al.

This work addresses the problem of anticipating user needs for proactive AI systems by predicting their next computer interaction, which is significant for developers of AI assistants.

Evgenii Rudakov, Jonathan Shock, Otto Lappi et al.

This addresses challenges in human-computer interaction, rehabilitation medicine, and motor control studies by providing a fast and accurate method for analyzing human movements.

Wujiang Xu, Zujie Liang, Kai Mei et al.

This addresses the need for more adaptive and context-aware memory management in LLM agents, representing a novel method rather than an incremental improvement.

Yiqian Yang

This provides a low-cost, accessible alternative to BCIs for motor-impaired users, enabling intuitive human-computer interaction in applications like assistive technology and entertainment.

Jiale Wei, Xiang Ying, Tao Gao et al.

This addresses the inefficiency of repeated data input for users interacting with various digital platforms, representing a novel approach rather than an incremental improvement.

Ying Xue, Jiaxi Jiang, Rayan Armani et al.

This addresses the challenge of multi-person motion capture in unconstrained environments for applications like virtual reality or sports analysis, representing a novel integration rather than an incremental improvement.

Siqi Zhu, David Zhang, Pedro Cisneros-Velarde et al.

This addresses the issue of misaligned LLM behavior for users in practical applications, offering a novel approach to enhance cooperative outcomes.

Yujia Qin, Yining Ye, Junjie Fang et al.

This addresses the challenge of automating GUI tasks for users and developers, offering a novel approach that reduces reliance on heavily wrapped commercial models and expert-crafted workflows.

Yuxiang Wei, Yanteng Zhang, Xi Xiao et al.

This work addresses the need for interpretable and generalizable brain-computer interfaces for neuroscience and medical applications, representing a novel method rather than an incremental improvement.