Web automation uses intelligent agents to perform high-level tasks by mimicking human interactions with webpages. Despite recent advances in LLM-based web agents, efficiently navigating complex, real-world webpages remains challenging due to massive DOM structures (10,000 ~ 100,000 tokens). Current approaches either truncate DOMs—losing vital information—or use inefficient heuristics and separate ranking models, failing to balance precision and scalability. We introduce Prune4Web, a novel paradigm that transforms DOM processing from LLM-based filtering to programmatic pruning. Our key innovation is DOM Tree Pruning Programming, where an LLM generates executable Python scoring programs to dynamically filter DOM elements based on semantic clues from decomposed sub-tasks. This approach eliminates the need for LLMs to process full DOMs, instead delegating traversal and scoring to lightweight, interpretable programs. The result is a 25 ~ 50 times reduction in candidate elements for grounding, enabling precise action localization without attention dilution. Additionally, we propose a data annotation method and a two-turn dialogue training strategy that jointly optimizes Planner, Programmatic Filter, and Grounder in a unified framework. Experiments demonstrate state-of-the-art performance. On our low-level task grounding task, our approach dramatically increases grounding accuracy from 46.80% to 88.28%, highlighting its effectiveness.

In the new era of wireless communication, there has been an increased interest in indoor positioning systems that propelled researchers to come up with various solutions. Fusing the fuzzy locations from Bluetooth (BT) beacons with the ones from pedestrian dead reckoning (PDR) comes out a promising solution to provide meter-level positioning without additional infrastructure. Despite the remarkable efforts the community put to build the system, it lacks the performance examination of large-scale deployments. In this report, we implement and deploy a real system in Guangzhou South Railway Station to enable a large scale indoor positioning service. The framework used Bluetooth beacons and pedestrian dead reckoning to calculate the estimated position of the user then refine the accuracy through a fuzzy fusion algorithm. We distribute up to 2849 beacons in the indoor space of 81654 square meters. When applied to the real ceiling with a height of 8m and above, our approach is still able to reliably achieve a high accuracy of 5 meters. Also in buildings whose outer walls are nonstructural but large glass curtain wall that wraps around the roof of the facility, the GPS signal could serve as useful complement under careful utilization; last but not least significant, in practice we incorporate our indoor positioning services into WeChat HyperText Markup Language (HTML) platform, we discover that the headings provided by HTML5 are not always correct, the orientation error scale has a strong correlation with the temperature of phone, the residual error is accumulated along with the time to make matters worse.

Cross-device interaction between multiple mobile devices is a popular field of research in HCI. However, the appropriate design of this interaction is still an open question, with competing approaches such as spatially-aware vs. spatially-agnostic techniques. In this paper, we present the results of a two-phase user study that explores this design space: In phase 1, we elicited gestures for typical mobile cross-device tasks from 4 focus groups (N=17). The results show that 71% of the elicited gestures were spatially-aware and that participants strongly associated cross-device tasks with interacting and thinking in space. In phase 2, we implemented one spatially-agnostic and two spatially-aware techniques from phase 1 and compared them in a controlled experiment (N=12). The results indicate that spatially-aware techniques are preferred by users and can decrease mental demand, effort, and frustration, but only when they are designed with great care. We conclude with a summary of findings to inform the design of future cross-device interactions.