This paper proposes FDALLM-Small, a unified and lightweight RF sensing framework that integrates Functional Data Analysis (FDA) with parameter efficiently tuned small language models. By transforming raw RF measurements into smooth and structured functional embeddings and encoding them into standardized functional prompts, the framework enables compact LLMs to perform classification and localization tasks with strong accuracy and robustness. Through LoRA based fine tuning, small LLMs effectively learn discriminative RF patterns while updating only a tiny fraction of model parameters, making the approach highly efficient and suitable for on device deployment. Experiments on the XRF55 and AdaRF datasets demonstrate that the FDA–prompting pipeline substantially boosts model performance, allowing small LLMs to surpass conventional deep learning baselines and approach the accuracy of large API based LLMs without relying on cloud computation. A scaling study further shows that smaller models consistently offer the best performance–efficiency trade offs, highlighting the intrinsic compatibility between FDA representations and compact architectures. These results confirm the practicality of FDALLM-Small as an edge friendly and computationally efficient solution for real world RF sensing applications.

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif, Christine de Kock, Nirmal Surange, Daniela Teodorescu, Ibrahim Said Ahmad, David Ifeoluwa Adelani, Alham Fikri Aji, Felermino D. M. A. Ali, Ilseyar Alimova, Vladimir Araujo, Nikolay Babakov, Naomi Baes, Ana-Maria Bucur, Andiswa Bukula, Guanqun Cao, Rodrigo Tufiño, Rendi Chevi, Chiamaka Ijeoma Chukwuneke, Alexandra Ciobotaru, Daryna Dementieva, Murja Sani Gadanya, Robert Geislinger, Bela Gipp, Oumaima Hourrane, Oana Ignat, Falalu Ibrahim Lawan, Rooweither Mabuya, Rahmad Mahendra, Vukosi Marivate, Alexander Panchenko, Andrew Piper, Charles Henrique Porto Ferreira, Vitaly Protasov, Samuel Rutunda, Manish Shrivastava, Aura Cristina Udrea, Lilian Diana Awuor Wanzare, Sophie Wu, Florian Valentin Wunderlich, Hanif Muhammad Zhafran, Tianhui Zhang, Yi Zhou, Saif M. Mohammad. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

In communication network management, mobile traffic prediction is vital for ensuring efficient system operation. Despite considerable progresses in applying neural networks for traffic prediction, traditional models often struggle to handle high-dimensional and time-dependent data. This paper addresses these challenges by proposing a novel framework that constructs prompts to enhance the predictive ability of large language models (LLMs) and their understanding of traffic data. Specifically, we leverage functional data analysis (FDA), a superior technique to traditional methods, to preprocess traffic data and extract features. Through extensive experiments on various LLMs with a real-world dataset, we validate the effectiveness and scalability of our proposed method, with performance improvements of up to 23.53 % and 21.34 % in mean squared error (MSE) and mean absolute error (MAE), respectively. Our results indicate a significant advance in predictive performance, providing a promising approach for future traffic data analysis.

Object manipulation for rearrangement into a specific goal state is a significant task for collaborative robots. Accurately determining object placement is a key challenge, as misalignment can increase task complexity and the risk of collisions, affecting the efficiency of the rearrangement process. Most current methods heavily rely on pre-collected datasets to train the model for predicting the goal position. As a result, these methods are restricted to specific instructions, which limits their broader applicability and generalisation. In this paper, we propose a framework of flexible language-conditioned object rearrangement based on the Large Language Model (LLM). Our approach mimics human reasoning by making use of successful past experiences as a reference to infer the best strategies to achieve a current desired goal position. Based on LLM’s strong natural language comprehension and inference ability, our method generalises to handle various everyday objects and free-form language instructions in a zero-shot manner. Experimental results demonstrate that our methods can effectively execute the robotic rearrangement tasks, even those involving long sequences of orders.

In communication network management, prediction of mobile network traffic is essential to ensure efficient system operation. Although significant progress has been made in the application of neural networks to traffic prediction tasks, traditional models still face considerable challenges when handling high-dimensional and highly time-dependent data. To address these issues, this paper proposes a new prediction framework that leverages large language models (LLMs), by constructing efficient prompts to enhance the ability of large language models (LLMs) in traffic prediction and improve their understanding of complex traffic patterns. Specifically, we introduce functional data analysis (FDA), a technique that offers superior capabilities compared to traditional methods in processing continuous and high-dimensional data structures, to preprocess traffic data and extract key features. Extensive experiments conducted on multiple LLMs using a real-world dataset validate the effectiveness and scalability of the proposed method. The experimental results demonstrate that the framework achieves significant improvements in predictive performance, providing a promising and efficient solution for traffic data analysis in future communication networks.

Recent years have witnessed rapid development of Wi-Fi sensing applications. However, the domain shift problem is still an open problem. Variations in environment, time, and detected objects can undermine the effectiveness of cross-domain sensing. This paper proposes a few-shot learning framework for Wi-Fi sensing that enables generalization to unseen domains given only a few samples. To better extract stable features, functional data analysis (FDA) is first employed as a preprocessing technique. We thoroughly evaluate our approach to different Wi-Fi sensing tasks: gesture recognition, and activity recognition. Our experimental results demonstrate that FDA assisted system improves cross-domain accuracy by 14%, 10%, and 8% on the respective tasks with five samples per class.

To assist robots in teleoperation tasks, haptic rendering which allows human operators access a virtual touch feeling has been developed in recent years. Most previous haptic rendering methods strongly rely on data collected by tactile sensors. However, tactile data is not widely available for robots due to their limited reachable space and the restrictions of tactile sensors. To eliminate the need for tactile data, in this paper we propose a novel method named as Vis2Hap to generate haptic rendering from visual inputs that can be obtained from a distance without physical interaction. We take the surface texture of objects as key cues to be conveyed to the human operator. To this end, a generative model is designed to simulate the roughness and slipperiness of the object's surface. To embed haptic cues in Vis2Hap, we use height maps from tactile sensors and spectrograms from friction coefficients as the intermediate outputs of the generative model. Once Vis2Hap is trained, it can be used to generate height maps and spectrograms of new surface textures, from which a friction image can be obtained and displayed on a haptic display. The user study demonstrates that our proposed Vis2Hap method enables users to access a realistic haptic feeling similar to that of physical objects. The proposed vision-based haptic rendering has the potential to enhance human operators' perception of the remote environment and facilitate robotic manipulation.

The missing signal caused by the objects being occluded or an unstable sensor is a common challenge during data collection. Such missing signals will adversely affect the results obtained from the data, and this issue is observed more frequently in robotic tactile perception. In tactile perception, due to the limited working space and the dynamic environment, the contact between the tactile sensor and the object is frequently insufficient and unstable, which causes the partial loss of signals, thus leading to incomplete tactile data. The tactile data will therefore contain fewer tactile cues with low information density. In this paper, we propose a tactile representation learning method, named TacMAE, based on Masked Autoencoder to address the problem of incomplete tactile data in tactile perception. In our framework, a portion of the tactile image is masked out to simulate the missing contact regions. By reconstructing the missing signals in the tactile image, the trained model can achieve a high-level understanding of surface geometry and tactile properties from limited tactile cues. The experimental results of tactile texture recognition show that TacMAE can achieve a high recognition accuracy of 71.4% in the zero-shot transfer and 85.8% after fine-tuning, which are 15.2% and 8.2% higher than the results without using masked modeling. The extensive experiments on YCB objects demonstrate the knowledge transferability of our proposed method and the potential to improve efficiency in tactile exploration.

We study the problem of learning to rank from multiple information sources. Though multi-view learning and learning to rank have been studied extensively leading to a wide range of applications, multi-view learning to rank as a synergy of both topics has received little attention. The aim of the paper is to propose a composite ranking method while keeping a close correlation with the individual rankings simultaneously. We present a generic framework for multi-view subspace learning to rank (MvSL2R), and two novel solutions are introduced under the framework. The first solution captures information of feature mappings from within each view as well as across views using autoencoder-like networks. Novel feature embedding methods are formulated in the optimization of multi-view unsupervised and discriminant autoencoders. Moreover, we introduce an end-to-end solution to learning towards both the joint ranking objective and the individual rankings. The proposed solution enhances the joint ranking with minimum view-specific ranking loss, so that it can achieve the maximum global view agreements in a single optimization process. The proposed method is evaluated on three different ranking problems, i.e., university ranking, multi-view lingual text ranking, and image data ranking, providing superior results compared to related methods.

Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed understanding of the surface textures via tactile sensing is essential for many of these tasks. Previous works on texture recognition using camera based tactile sensors have been limited to treating all regions in one tactile image or all samples in one tactile sequence equally, which includes much irrelevant or redundant information. In this paper, we propose a novel Spatio-Temporal Attention Model (STAM) for tactile texture recognition, which is the very first of its kind to our best knowledge. The proposed STAM pays attention to both spatial focus of each single tactile texture and the temporal correlation of a tactile sequence. In the experiments to discriminate 100 different fabric textures, the spatially and temporally selective attention has resulted in a significant improvement of the recognition accuracy, by up to 18.8%, compared to the non-attention based models. Specifically, after introducing noisy data that is collected before the contact happens, our proposed STAM can learn the salient features efficiently and the accuracy can increase by 15.23% on average compared with the CNN based baseline approach. The improved tactile texture perception can be applied to facilitate robot tasks like grasping and manipulation.

In this paper, the problem of multi-view embedding from different visual cues and modalities is considered. We propose a unified solution for subspace learning methods using the Rayleigh quotient, which is extensible for multiple views, supervised learning, and nonlinear embeddings. Numerous methods including canonical correlation analysis, partial least square regression, and linear discriminant analysis are studied using specific intrinsic and penalty graphs within the same framework. Nonlinear extensions based on kernels and (deep) neural networks are derived, achieving better performance than the linear ones. Moreover, a novel multi-view modular discriminant analysis is proposed by taking the view difference into consideration. We demonstrate the effectiveness of the proposed multi-view embedding methods on visual object recognition and cross-modal image retrieval, and obtain superior results in both applications compared to related methods.

Energy management is indispensable in the smart grid, which integrates more renewable energy resources, such as solar and wind. Because of the intermittent power generation from these resources, precise power forecasting has become crucial to achieve efficient energy management. In this paper, we propose a novel adaptive learning hybrid model (ALHM) for precise solar intensity forecasting based on meteorological data. We first present a time-varying multiple linear model (TMLM) to capture the linear and dynamic property of the data. We then construct simultaneous confidence bands for variable selection. Next, we apply the genetic algorithm back propagation neural network (GABP) to learn the nonlinear relationships in the data. We further propose ALHM by integrating TMLM, GABP, and the adaptive learning online hybrid algorithm. The proposed ALHM captures the linear, temporal, and nonlinear relationships in the data, and keeps improving the predicting performance adaptively online as more data are collected. Simulation results show that ALHM outperforms several benchmarks in both short-term and long-term solar intensity forecasting.

A novel multi-view nonparametric discriminant analysis method is proposed for the application of cross-modal image retrieval and zero-shot recognition. We exploit the class boundary structure and discrepancy information of the available views in order to formulate an optimization criterion, which is automatically adjusted to the multi-view class structures. The proposed method allows for multiple projection directions, by relaxing the Gaussian distribution assumption of related methods. The experiments demonstrate that the proposed method can achieve superior results comparing to several existing methods.