Mehran Kazemi, Bahare Fatemi, Hritik Bansal, John Palowitch, Chrysovalantis Anastasiou, Sanket Vaibhav Mehta, Lalit K Jain, Virginia Aglietti, Disha Jindal, Peter Chen, Nishanth Dikkala, Gladys Tyen, Xin Liu, Uri Shalit, Silvia Chiappa, Kate Olszewska, Yi Tay, Vinh Q. Tran, Quoc V Le, Orhan Firat. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy preference pairs that induce similar likelihood for preferred and dispreferred responses. The contributions of this paper are two-fold. First, we propose a new preference alignment method based on zeroth-order, comparison-based optimization via comparison oracles and provide convergence guarantees for its basic scheme. Second, we improve our method using some heuristics and conduct the experiments to demonstrate the flexibility and compatibility of practical scheme in improving the performance of LLMs using noisy preference pairs. Evaluations are conducted across multiple base and instruction-tuned models (Mistral-7B, Llama-3-8B and Gemma-2-9B) with benchmarks (AlpacaEval 2, MT-Bench and Arena-Hard). Experimental results show the effectiveness of our method as an alternative to addressing the limitations of existing direct alignment methods. A highlight of our work is that we evidence the importance of designing specialized methods for preference pairs with distinct likelihood margin, which complements the recent findings in Razin et al (2025).

A warm welcome to the 2024 IEEE World Congress on Services (SERVICES). With Professor Zhi Jin and Professor Michael Sheng serving as the Congress General Chairs, I trust everyone will have a rewarding experience participating in the IEEE Computer Society's flagship annual event in services computing, whether attending on-site or remotely.

A warm welcome to the 2024 IEEE World Congress on Services (SERVICES). With Professor Zhi Jin and Professor Michael Sheng serving as the Congress General Chairs, I trust everyone will have a rewarding experience participating in the IEEE Computer Society's flagship annual event in services computing, whether attending on-site or remotely.

Robot vacuums have become a ubiquitous appliance, offering un- paralleled convenience and efficiency in maintaining cleanliness in both residential and commercial spaces. However, these devices also present a convenient method for attackers to gather information about the robot's surroundings. In this study, we investigate the feasibility of acoustic side-channel attacks on robot vacuums and demonstrate that sensitive information can be easily obtained by analyzing the sound produced by the robot. We extract various characteristic features and spectrograms from the sound emitted during robot movement and classify them using Multilayer Perception and Convolutional Neural Network. The evaluation results demonstrate the effectiveness of the acoustic attacks, with both machine learning models achieving more than 95% accuracy in classifying the robot's movement based on acoustic signals. Using our ML model, we demonstrate that robot cleaning path can be effectively identified with 96% accuracy. To mitigate such a threat, we perform a simulation where random noise is added to the sound samples, which effectively reduce the motion identification accuracy to 43%.

Exploratory data science is driving new platforms that assist data scientists with everyday tasks, such as integration and wrangling, to assemble training datasets. Such tools take scientists' work-in-progress data as a search object (table or JSON) and find relevant supplementary data from an organizational data lake , which can be unioned or joined with the current data. Existing data lake search tools find single , relational tables to match or join with a search object. Yet many data science applications revolve around hierarchical data, which can only be matched by creating views that simultaneously join and transform several tables in the data lake. In this paper, we extend the Juneau data lake search system [46] for this broader class of matches at scale. Our contribution is a general framework for efficiently merging ranked results to match hierarchical data, leveraging novel techniques for indexing and sketching, and incorporating existing single-table search techniques and ranking functions. We experimentally validate our methods' benefits and broad applicability using real data from data science computational notebooks. Our results indicate that, with different ranking functions, our approach can return the optimal set of views up to 4.8x faster and 43% more related compared to heuristics, and increase the data domain coverage by up to 28%. In a case study to show the utility of our results to data science downstream tasks, we reduce regression error by up to 6.6%, and improve classification accuracy by up to 19.5%.

One of the ultimate goals of several learning analytics (LA) initiatives is to close the loop and support students’ and teachers’ reflective practices. Although there has been a proliferation of end-user interfaces (often in the form of dashboards), various limitations have already been identified in the literature such as key stakeholders not being involved in their design, little or no account for sense-making needs, and unclear effects on teaching and learning. There has been a recent call for human-centred design practices to create LA interfaces in close collaboration with educational stakeholders to consider the learning design, and their authentic needs and pedagogical intentions. This paper addresses the call by proposing a question-driven LA design approach to ensure that end-user LA interfaces explicitly address teachers’ questions. We illustrate the approach in the context of synchronous online activities, orchestrated by pairs of teachers using audio-visual and text-based tools (namely Zoom and Google Docs). This study led to the design and deployment of an open-source monitoring tool to be used in real-time by teachers when students work collaboratively in breakout rooms, and across learning spaces.

One of the ultimate goals of several learning analytics (LA) initiatives is to close the loop and support students' and teachers' reflective practices. Although there has been a proliferation of end-user interfaces (often in the form of dashboards), various limitations have already been identified in the literature such as little account for sensemaking needs. This paper addresses these limitations by proposing a question-driven LA design approach to ensure that end-user LA interfaces explicitly address teachers' questions. We illustrate this in the context of synchronous online activities orchestrated by pairs of teachers using audio-visual and text-based tools (Zoom and Google Docs). This led to the design of an open-source monitoring tool to be used in real-time by teachers when students work collaboratively in breakout rooms, and across learning spaces.

We have seen a dramatic increase in the adoption of teleconferencing systems such as Zoom for remote teaching and working. Although designed primarily for traditional video conferencing scenarios, these platforms are actually being deployed in many diverse contexts. As such, Zoom offers little to aid hosts' understanding of attendee participation and often hinders participant agency. We introduce ZoomSense : an open-source, scalable infrastructure built upon 'virtual meeting participants', which exposes real-time meta-data, meeting content and host controls through an easy to use abstraction - so that developers can rapidly and sustainably augment Zoom.

With the development of depth sensors, 3D point cloud upsampling that generates a high-resolution point cloud given a sparse input becomes emergent. However, many previous works focused on single 3D object reconstruction and refinement. Although a few recent works began to discuss 3D structure refine-ment for a more complex scene, they do not target LiDAR-based point clouds, which have density imbalance issues from near to far. This paper proposed DensER, a Density-imbalance-Eased regional Representation. Notably, to learn robust representations and model local geometry under imbalance point density, we designed density-aware multiple receptive fields to extract the regional features. Moreover, founded on the patch reoccurrence property of a nature scene, we proposed a density-aided attentive module to enrich the extracted features of point-sparse areas by referring to other non-local regions. Finally, by coupling with novel manifold-based upsamplers, DensER shows the ability to super-resolve LiDAR-based whole-scene point clouds. The exper-imental results show DensER outperforms related works both in qualitative and quantitative evaluation. We also demonstrate that the enhanced point clouds can improve downstream tasks such as 3D object detection and depth completion.

The papers in this special section focus on blockchain-based computing services. Blockchain has become a hot research area in academia and industry. A blockchain is a continuously growing list of records of value-transferred transactions maintained by a peer-to-peer network through a distributed consensus mechanism. Blockchain technology has promising characteristics regarding decentralization, persistency, anonymity and auditability that could greatly improve the cost-effectiveness of inter-organization business processes. Blockchain can be applied to many fields of services computing, e.g., big data, cloud computing, digital economy, intelligent contracts, Internet-of-Things, securities, etc.Non-functional innovations in blockchain-based services computing are essential to improving the efficacy of blockchain. These paper focus on presenting novel approaches to integrate blockchain with services computing techniques as well as factual insights on new rising challenges and requirements in achieving this goal.

This paper presents our experience in constructing an electronic whiteboard-based computer laboratory for teaching digital signal processing (DSP) courses in Australian undergraduate and postgraduate programs. Student interaction with the electronic whiteboard-based tutorial class environment is also reported. Away from the laboratory, DSP lectures were presented using a tablet PC as a digital whiteboard. This supported high quality handwriting annotation of lecture slides, and overcame the limited flexibility present in the existing PowerPoint mode of lecture delivery. For selected self-paced tutorial questions, solutions were provided in electronic format comprising the lecturer's handwritten explanation on a blank slide, input using the tablet PC, combined with audio commentary. An evaluation of student opinions towards this multi-mode delivery of DSP education was illuminating, and the overall experience with these technological aids was that signal processing could be effectively and naturally taught with high student attention span.

The authors show how to use the timed Petri net with stacks (TPNS-net) to describe asynchronous concurrent distributed computing systems (DCS) which are based on the environment of loosely coupled computing systems. They also present methods for detecting types of DCS deadlocks such as cycle waiting, hold and wait, and exclusive access. It is shown that TPNS-net permits a process to request more than one resource at a time, express the dynamic state of the system, and increase the system parallelism.>