Knowledge Graphs (KGs) are fundamental for grounding Large Language Models (LLMs) in factually consistent reasoning across diverse data-mining tasks. However, when reasoning over complex graph topologies, LLMs can be brittle in maintaining structural consistency and may rely on spurious correlations. We propose SKILL (...
Lei Gao, Ben Zhang, Jin-Chuan Zhang et al.· Proceedings of the 35th ACM...· 0 citations
Knowledge Graphs (KGs) are fundamental for grounding Large Language Models (LLMs) in factually consistent reasoning across diverse data-mining tasks. However, when reasoning over complex graph topologies, LLMs can be brittle in maintaining structural consistency and may rely on spurious correlations. We propose SKILL (...
Lei Gao, Ben Zhang, Jin-Chuan Zhang et al.· Proceedings of the 35th ACM...· 0 citations
Ten-finger surface typing promises a portable alternative to physical keyboards and touchscreens, making it well-suited for mobile scenarios, but remains challenging to balance sensing cost with input performance. We ask whether it can be enabled with two IMU rings, without relying on bulky wearables or continuous visi...
Zhuo-Jun Li, Chun Yu, Zhe He et al.· Proceedings of the 39th Annu...· 0 citations
Current multi-view gaze estimation remains limited by existing datasets, insufficient exploitation of complementary cross-view information, and evaluation focused primarily on average gaze error. We address these limitations through a more systematic study of multi-view gaze estimation. First, we introduce PrismGaze, a...
Chang Liu, Jia-Qi Liu, Cheng-Wen Zhang et al.· 1 citation
Downstream RLHF experiments additionally show that using DRM as the training-time reward leads to improved policy performance, directly validating the practical benefit of diffusion-based reward modeling for RLHF training.
Xiang-Yang Wang, Bing-Xiang He, Ze-Yuan Liu et al.· arXiv.org· 0 citations
This work explores laughter as a naturally occurring, sparse index for constructing contextualized personal records to support later reconstruction and reflection and inform self-tracking designs that use sparse affective indices to organize contextual records for reconstruction and reflection.
Jun Fang, Jia-Jin Li, Yun-Tao Wang et al.· 0 citations
In human-LLM content co-generation, AI-generated information can enter final artifacts without being adequately processed by users, creating risks when artifacts are shared or acted upon. We study whether recognition-level uptake of atomic information units can be assessed in open-ended co-generation and predicted from...
Yu Mei, Feng-You Zu, Rui-Wen Zhang et al.· 0 citations
The architectural improvements and novel training recipe allow PaGE to achieve state-of-the-art performance on several gaze estimation tasks, outperforming humans in 7 out of 9 metrics while reducing the human-AI gap by at least 60% in the remaining 2.
Zhou-Tong Ye, Cheng-Wen Zhang, Zhai-Bin Cui et al.· arXiv.org· 0 citations
U-Lens improves verification efficiency and effort allocation, reduced perceived workload, and strengthened support across all three stages of uncertainty management, and reframes uncertainty support for generative AI from text-centered cues to a user-centered process of interpreting, evaluating, and acting on uncertai...
Yu Mei, Qingyue Zhuang, Jie Cai et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.