Evaluating LLMs on Chinese Idiom Translation

Idioms, whose figurative meanings usually differ from their literal interpretations, are common in everyday language, especially in Chinese, where they often contain historical references and follow specific structural patterns. Despite recent progress in machine translation with large language models, little is known about Chinese idiom translation. In this work, we introduce IdiomEval, a framework with a comprehensive error taxonomy for Chinese idiom translation. We annotate 900 translation pairs from nine modern systems, including GPT-4o and Google Translate, across four domains: web, news, Wikipedia, and social media. We find these systems fail at idiom translation, producing incorrect, literal, partial, or even missing translations. The best-performing system, GPT-4, makes errors in 28% of cases. We also find that existing evaluation metrics measure idiom quality poorly with Pearson correlation below 0.48 with human ratings. We thus develop improved models that achieve F$_1$ scores of 0.68 for detecting idiom translation errors.

Communication Efficient Robotic Mixed Reality with Gaussian Splatting Cross-Layer Optimization

Realizing low-cost communication in robotic mixed reality (RoboMR) systems presents a challenge, due to the necessity of uploading high-resolution images through wireless channels. This paper proposes Gaussian splatting (GS) RoboMR (GSMR), which enables the simulator to opportunistically render a photo-realistic view from the robot's pose by calling ``memory'' from a GS model, thus reducing the need for excessive image uploads. However, the GS model may involve discrepancies compared to the actual environments. To this end, a GS cross-layer optimization (GSCLO) framework is further proposed, which jointly optimizes content switching (i.e., deciding whether to upload image or not) and power allocation (i.e., adjusting to content profiles) across different frames by minimizing a newly derived GSMR loss function. The GSCLO problem is addressed by an accelerated penalty optimization (APO) algorithm that reduces computational complexity by over $10$x compared to traditional branch-and-bound and search algorithms. Moreover, variants of GSCLO are presented to achieve robust, low-power, and multi-robot GSMR. Extensive experiments demonstrate that the proposed GSMR paradigm and GSCLO method achieve significant improvements over existing benchmarks on both wheeled and legged robots in terms of diverse metrics in various scenarios. For the first time, it is found that RoboMR can be achieved with ultra-low communication costs, and mixture of data is useful for enhancing GS performance in dynamic scenarios.

Energy-Efficient Hybrid Beamfocusing for Near-Field Integrated Sensing and Communication

Integrated sensing and communication (ISAC) is a pivotal component of sixth-generation (6G) wireless networks, leveraging high-frequency bands and massive multiple-input multiple-output (M-MIMO) to deliver both high-capacity communication and high-precision sensing. However, these technological advancements lead to significant near-field effects, while the implementation of M-MIMO \mbox{is associated with considerable} hardware costs and escalated power consumption. In this context, hybrid architecture designs emerge as both hardware-efficient and energy-efficient solutions. Motivated by these considerations, we investigate the design of energy-efficient hybrid beamfocusing for near-field ISAC under two distinct target scenarios, i.e., a point target and an extended target. Specifically, we first derive the closed-form Cram\'{e}r-Rao bound (CRB) of joint angle-and-distance estimation for the point target and the Bayesian CRB (BCRB) of the target response matrix for the extended target. Building on these derived results, we minimize the CRB/BCRB by optimizing the transmit beamfocusing, while ensuring the energy efficiency (EE) of the system and the quality-of-service (QoS) for communication users. To address the resulting \mbox{nonconvex problems}, we first utilize a penalty-based successive convex approximation technique with a fully-digital beamformer to obtain a suboptimal solution. Then, we propose an efficient alternating \mbox{optimization} algorithm to design the analog-and-digital beamformer. \mbox{Simulation} results indicate that joint distance-and-angle estimation is feasible in the near-field region. However, the adopted hybrid architectures inevitably degrade the accuracy of distance estimation, compared with their fully-digital counterparts. Furthermore, enhancements in system EE would compromise the accuracy of target estimation, unveiling a nontrivial tradeoff.

Human-Centered Human-AI Interaction (HC-HAII): A Human-Centered AI Perspective

This chapter systematically promotes an emerging interdisciplinary field of human-artificial intelligence interaction (human-AI interaction, HAII) from a human-centered AI (HCAI) perspective. It introduces a framework of human-centered HAII (HC-HAII). HC-HAII places humans at the core of HAII research and applications, emphasizing the importance of adopting a human-centered approach over a technology-centered one. The chapter presents the HC-HAII methodology, including human-centered methods, process, interdisciplinary teams, and multi-level design paradigms. It also highlights key research challenges and future directions. As the first chapter, this chapter also provides a structural overview of this book, which brings together contributions from an interdisciplinary community of researchers and practitioners to advance the theory, methodology, and applications of HCAI in diverse domains of HAII. The purpose of this chapter is to provide a fundamental framework for this book, centered on HAII research and applications based on the HCAI approach, which will pave the way for the content of subsequent chapters.

Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges

Tables have gained significant attention in large language models (LLMs) and multimodal large language models (MLLMs) due to their complex and flexible structure. Unlike linear text inputs, tables are two-dimensional, encompassing formats that range from well-structured database tables to complex, multi-layered spreadsheets, each with different purposes. This diversity in format and purpose has led to the development of specialized methods and tasks, instead of universal approaches, making navigation of table understanding tasks challenging. To address these challenges, this paper introduces key concepts through a taxonomy of tabular input representations and an introduction of table understanding tasks. We highlight several critical gaps in the field that indicate the need for further research: (1) the predominance of retrieval-focused tasks that require minimal reasoning beyond mathematical and logical operations; (2) significant challenges faced by models when processing complex table structures, large-scale tables, length context, or multi-table scenarios; and (3) the limited generalization of models across different tabular representations and formats.

The Singapore Consensus on Global AI Safety Research Priorities

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The "2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).

Human-Centered Human-AI Collaboration (HCHAC)

In the intelligent era, the interaction between humans and intelligent systems fundamentally involves collaboration with autonomous intelligent agents. Human-AI Collaboration (HAC) represents a novel type of human-machine relationship facilitated by autonomous intelligent machines equipped with AI technologies. In this paradigm, AI agents serve not only as auxiliary tools but also as active teammates, partnering with humans to accomplish tasks collaboratively. Human-centered AI (HCAI) emphasizes that humans play critical leadership roles in the collaboration. This human-led collaboration imparts new dimensions to the human-machine relationship, necessitating innovative research perspectives, paradigms, and agenda to address the unique challenges posed by HAC. This chapter delves into the essence of HAC from the human-centered perspective, outlining its core concepts and distinguishing features. It reviews the current research methodologies and research agenda within the HAC field from the HCAI perspective, highlighting advancements and ongoing studies. Furthermore, a framework for human-centered HAC (HCHAC) is proposed by integrating these reviews and analyses. A case study of HAC in the context of autonomous vehicles is provided, illustrating practical applications and the synergistic interactions between humans and AI agents. Finally, it identifies potential future research directions aimed at enhancing the effectiveness, reliability, and ethical integration of human-centered HAC systems in diverse domains.

Task-Oriented Low-Label Semantic Communication With Self-Supervised Learning

Task-oriented semantic communication enhances transmission efficiency by conveying semantic information rather than exact messages. Deep learning (DL)-based semantic communication can effectively cultivate the essential semantic knowledge for semantic extraction, transmission, and interpretation by leveraging massive labeled samples for downstream task training. In this paper, we propose a self-supervised learning-based semantic communication framework (SLSCom) to enhance task inference performance, particularly in scenarios with limited access to labeled samples. Specifically, we develop a task-relevant semantic encoder using unlabeled samples, which can be collected by devices in real-world edge networks. To facilitate task-relevant semantic extraction, we introduce self-supervision for learning contrastive features and formulate the information bottleneck (IB) problem to balance the tradeoff between the informativeness of the extracted features and task inference performance. Given the computational challenges of the IB problem, we devise a practical and effective solution by employing self-supervised classification and reconstruction pretext tasks. We further propose efficient joint training methods to enhance end-to-end inference accuracy over wireless channels, even with few labeled samples. We evaluate the proposed framework on image classification tasks over multipath wireless channels. Extensive simulation results demonstrate that SLSCom significantly outperforms conventional digital coding methods and existing DL-based approaches across varying labeled data set sizes and SNR conditions, even when the unlabeled samples are irrelevant to the downstream tasks.

RemoteSAM: Towards Segment Anything for Earth Observation

We aim to develop a robust yet flexible visual foundation model for Earth observation. It should possess strong capabilities in recognizing and localizing diverse visual targets while providing compatibility with various input-output interfaces required across different task scenarios. Current systems cannot meet these requirements, as they typically utilize task-specific architecture trained on narrow data domains with limited semantic coverage. Our study addresses these limitations from two aspects: data and modeling. We first introduce an automatic data engine that enjoys significantly better scalability compared to previous human annotation or rule-based approaches. It has enabled us to create the largest dataset of its kind to date, comprising 270K image-text-mask triplets covering an unprecedented range of diverse semantic categories and attribute specifications. Based on this data foundation, we further propose a task unification paradigm that centers around referring expression segmentation. It effectively handles a wide range of vision-centric perception tasks, including classification, detection, segmentation, grounding, etc, using a single model without any task-specific heads. Combining these innovations on data and modeling, we present RemoteSAM, a foundation model that establishes new SoTA on several earth observation perception benchmarks, outperforming other foundation models such as Falcon, GeoChat, and LHRS-Bot with significantly higher efficiency. Models and data are publicly available at https://github.com/1e12Leon/RemoteSAM.

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?

Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings.