The recent DeepSeek-R1 has showcased the emergence of reasoning capabilities in large language models (LLMs) through reinforcement learning (RL) with rule-based rewards. Despite its success in language tasks, its application in multimodal domains, particularly in graphic user interface (GUI) agent tasks, remains under-explored. To address this gap, we propose UI-R1, the first framework to investigate how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks. UI-R1 introduces a novel rule-based action reward scheme, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO). To further improve efficiency at inference time, we present UI-R1-Efficient, a two-stage training paradigm that reduces reasoning length while boosting overall performance. In addition, we construct a compact yet high-quality dataset containing 2K challenging tasks across five prevalent mobile device action types. Experiments show that our proposed models (e.g., UI-R1-3B) achieve substantial improvements over the base model (Qwen2.5-VL-3B) on both in-domain (ID) and out-of-domain (OOD) tasks, with average accuracy gains of 18.3% on ScreenSpot, 6.0% on ScreenSpot-Pro, and 10.9% on ANDROIDCONTROL. Moreover, our efficient versions deliver competitive performance compared to considerably larger state-of-the-art models, underscoring the potential of reinforcement learning to advance GUI control and paving the way for future research in Human-Computer Interaction (HCI).

Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, WenHao Wang, Yuehao Huang, Yuxiang Chai, Zhaolu Kang, Yaxuan Guo, Hao Wang, Kexin Zhang, Liang Liu, Yong Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Pruning is a critical strategy for compressing trained large language models (LLMs), aiming at substantial memory conservation and computational acceleration without compromising performance.However, existing pruning methods typically necessitate inefficient retraining for billion-scale LLMs or rely on heuristically designed metrics to determine pruning masks, leading to performance degradation.This paper presents, for the first time, a LASSO-like convex optimization model crafted to induce sparsity in LLMs.By leveraging FISTA, we introduce FISTAPruner, a novel method that includes a cumulative error elimination mechanism within decoder layers and supports parallel pruning for unstructured pruning.Additionally, we extend this method to 2:4 semistructured pruning.We comprehensively evaluate FISTAPruner on models such as OPT, LLaMA, and Qwen variants with 125M to 70B parameters under unstructured and 2:4 semistructured sparsity, showcasing superior performance over existing methods across various language benchmarks.Notably, it can remove 50% of the model parameters for LLaMA-3-70B while retaining 98.6% and 95.6% of the zero-shot task performance under these two sparsity patterns, respectively.

Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native support for mixed-precision General Matrix Multiplication (mpGEMM), resulting in inefficient dequantization-based implementations. Moreover, uniform quantization methods often fail to capture weight distributions adequately, leading to performance degradation. We propose GANQ (GPU-Adaptive Non-Uniform Quantization), a layer-wise post-training non-uniform quantization framework optimized for hardware-efficient lookup table-based mpGEMM. GANQ achieves superior quantization performance by utilizing a training-free, GPU-adaptive optimization algorithm to efficiently reduce layer-wise quantization errors. Extensive experiments demonstrate GANQ’s ability to reduce the perplexity gap from the FP16 baseline compared to state-of-the-art methods for both 3-bit and 4-bit quantization. Furthermore, when deployed on a single NVIDIA RTX 4090 GPU, GANQ’s quantized models achieve up to 2.57$\times$ speedup over the baseline, advancing memory and inference efficiency in LLM deployment.

Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human intent, even when object locations are unknown. However, traditional data-driven DDN methods rely on pre-collected data for model training and decision-making, limiting their generalization capability in unseen scenarios. In this paper, we propose CogDDN, a VLM-based framework that emulates the human cognitive and learning mechanisms by integrating fast and slow thinking systems and selectively identifying key objects essential to fulfilling user demands. CogDDN identifies appropriate target objects by semantically aligning detected objects with the given instructions. Furthermore, it incorporates a dual-process decision-making module, comprising a Heuristic Process for rapid, efficient decisions and an Analytic Process that analyzes past errors, accumulates them in a knowledge base, and continuously improves performance. Chain of Thought (CoT) reasoning strengthens the decision-making process. Extensive closed-loop evaluations on the AI2Thor simulator with the ProcThor dataset show that CogDDN outperforms single-view camera-only methods by 15%, demonstrating significant improvements in navigation accuracy and adaptability. The project page is available at https://yuehaohuang.github.io/CogDDN/.

In cloud ecosystems, managing bandwidth costs is pivotal for both operational efficiency and service quality. This paper tackles the cloud-edge traffic allocation problem, particularly optimizing for the 95th percentile billing scheme, which is widely employed across various cloud computing scenarios by Internet Service Providers but has yet to be efficiently addressed. We introduce a mathematical model for this issue, confirm its NP-hard complexity, and reformulate it as a mixed-integer programming (MIP). The intricacy of the problem is further magnified by the scale of the cloud ecosystem, involving numerous data centers, client groups, and long billing cycles. Based on a structural analysis of our MIP model, we propose a two-stage solution strategy that retains optimality. We introduce the Circling Reduction Algorithm (CRA), a polynomial-time algorithm based on a rigorously derived lower bound for the objective value, to efficiently determine the binary variables in the first stage, while the remaining linear programming problem in the second stage can be easily resolved. Using the CRA, we develop algorithms for both offline and online traffic allocation scenarios and validate them on real-world datasets from the cloud provider under study. In offline scenarios, our method delivers up to 66.34% cost savings compared to a commercial solver, while also significantly improving computational speed. Additionally, it achieves an average of 14% cost reduction over the current solution of the studied cloud provider. For online scenarios, we achieve an average cost-saving of 8.64% while staying within a 9% gap of the theoretical optimum.

Though GPS-based human trajectory data have been commonly used in travel surveys and human mobility studies, missing data or data gaps that are intrinsically relevant to research reliability remain a critical and challenging issue. This study proposes a novel framework for imputing data gaps based on frequent-pattern mining and time geography, which allows for considering spatio-temporal travel restrictions during imputation by evaluating the spatio-temporal topology relations between the space-time prisms of gaps and corresponding frequent activities or trips. For the validation, the proposed framework is applied to raw GPS trajectories that were collected from 139 participants in Switzerland. In the case study, the temporal and spatio-temporal gaps are artificially generated by randomly choosing activities and trips from the trajectory data. Through comparing the mobility indicators (i.e. duration and distance) calculated from raw data, imputed data, and data with gaps, we quantitatively evaluate the performance of the proposed method in terms of Pearson correlation coefficients and deviation. We further compare the framework with the shortest path interpolation method based on the generated spatio-temporal gaps. The comparison results demonstrate the performance and advantage of the proposed method in imputing gaps from GPS-based human movement data.

Movement patterns of intra-urban goods/things and the ways they differ from human mobility and traffic flow patterns have seldom been explored due to data access and methodological limitations, especially from systemic and long timescale perspectives. However, urban logistics big data are increasingly available, enabling unprecedented spatial and temporal resolutions to this issue. This research proposes an analytical framework for exploring intra-urban goods movement patterns by integrating spatial analysis, network analysis and spatial interaction analysis. Using daily urban logistics big data (over 10 million orders) provided by the largest online logistics company in Hong Kong (GoGoVan) from 2014 to 2016, we analyzed two spatial characteristics (displacement and direction) of urban goods movement. Results showed that the distribution of goods displaceFower law or exponential distribution of human mobility trends. The origin–destination flows of goods were used to build a spatially embedded network, revealing that Hong Kong became increasingly connected through intra-urban freight movement. Finally, spatial interaction characteristics were revealed using a fitting gravity model. Distance lacked substantial influence on the spatial interaction of goods movement. These findings have policy implications to intra-urban logistics and urban transport planning.

Spatial clustering can be used to discover hotspots in trajectory data. A trajectory clustering approach based on decision graph and data field is proposed as an effective method to select parameters for clustering, to determine the number of clusters, and to identify cluster centers. Synthetic data and real-world taxi trajectory data are utilized to demonstrate the effectiveness of the proposed approach. Results show that the proposed method can automatically determine the parameters for clustering as well as perform efficiently in trajectory clustering. Hotspots are identified and visualized during different times of a single day and at the same times on different days. The dynamic patterns of hotspots can be used to identify crowded areas and events, which are crucial for urban transportation planning and management.

Peer-to-peer networks offer advantages over traditional client-server networking models, such as the lack of a need for connectivity to trusted intermediary hosts or servers and the use of less costly communication links. While they have become popular in the wired broadband environment, they have not yet been effectively adapted to the resource-constrained mobile network environment. They promise significant potential in applications such as the sharing of files like multimedia and operating system updates between mobile devices. However, the peer-to-peer model faces unique challenges in the mobile context, such as limitations on processing power, on-board device memory, wireless data bandwidth, and available battery energy. We propose a high-level framework for a peer-to-peer protocol with these specific constraints addressed. In addition, we investigate the feasibility of a practical implementation of a peer-to-peer file sharing model on smartphones, including an analysis of how performance is impacted by various variables that can be dynamically controlled in the protocol. Through experimentation on leading smartphones, we have found various optimal strategies, including minimizing the upload-to-download ratio to conserve battery life, using larger file segments to increase throughput, and using sockets to decrease memory overhead.