Virtual assistants (VAs) are increasingly positioned not just as tools, but as potential social companions—capable of offering either emotional or informational support. Yet, how these forms of support should adapt to varying task difficulties and embodiment styles remains underexplored. We conducted two user studies with cognitive and physical tasks to investigate how support type (emotional vs. informational) shapes user perceptions across variations in task difficulty (easy vs. hard) and embodiment (non-embodied vs. embodied). In Study 1, emotional support positively influenced users’ impressions of VA in easy tasks, while informational support was more effective in difficult tasks. In Study 2, participants also preferred emotional support for easy tasks, but differences between support types were less pronounced for difficult tasks. Notably, embodiment exerted no significant influence in either study. These findings underscore the role of context in shaping effective support strategies, offering design insights for VAs as social companions.

Empathy modeling in online interactions presents a significant challenge due to its dynamic, context-sensitive, and bidirectional nature. To address these complexities, we propose the Bi-directional MLP-Mixer (Bi-Mixer) and dynamic weights fusion model—a novel neural architecture that captures temporal dependencies in both forward and reverse directions and performs dynamic multi-modal fusion using a cross-attention mechanism. The model adaptively reweights input from visual, audio, text, and biological modalities based on contextual cues, enabling more accurate real-time empathy prediction. To support the training and evaluation of our proposed model, we build the Multi-modal online interaction EMPathy (Multi-EMP) dataset, consisting of unscripted dyadic conversations recorded through online video conferencing. The dataset includes four synchronized modalities: video, audio, text, and bio-signals such as electrodermal activity, blood volume pulse, temperature, and metabolic equivalent of task. It enables dual empathy assessment based on both explicit self-reports and computed emotional alignment between speaker and listener. Our contributions include: (1) the Bi-Mixer and dynamic weights fusion model for bidirectional and adaptive multi-modal representation learning, (2) the release of a comprehensive multi-modal dataset for naturalistic empathy research, and (3) a dual-perspective framework for empathy evaluation.

Audio-driven talking head generation requires precise synchronization between facial animations and audio signals. This paper introduces ATL-Diff, a novel approach addressing synchronization limitations while reducing noise and computational costs. Our framework features three key components: a Landmark Generation Module converting audio to facial landmarks, a Landmarks-Guide Noise approach that decouples audio by distributing noise according to landmarks, and a 3D Identity Diffusion network preserving identity characteristics. Experiments on MEAD and CREMA-D datasets demonstrate that ATL-Diff outperforms state-of-the-art methods across all metrics. Our approach achieves near real-time processing with high-quality animations, computational efficiency, and exceptional preservation of facial nuances. This advancement offers promising applications for virtual assistants, education, medical communication, and digital platforms. The source code is available at: https://github.com/sonvth/ATL-Diff

Fair competition has become a core value in sports However, the foundation of trust in sports is shaking as doping cases increase Doping is the act of athletes using prohibited drugs Among the drugs, it is easy to classify whether or not these drugs are prohibited drugs among the pills, but as the number of drugs increases, there is inevitably a limit to human ability In this study, AI based pill images are analyzed to identify prohibited drugs A model that automatically classifies drugs was produced using oral drug images Using the dataset provided by AI Hub, a model was produced by learning 160 056 images of 500 oral drugs By applying the CNN model and the SIFT algorithm, a model was produced to analyze and classify external characteristics such as size, color, and shape of a drug Finally, this model had a high classification accuracy of 96 5

People often attempt to mask their true emotions through deliberate facial expressions, but such efforts are not always successful. In contrast, emotional concealment could be more easily achieved in Virtual Reality (VR) when appropriate functionalities are available. This study introduces three techniques in VR that enable users to manually adjust emotional facial expression while still reflecting real-time facial tracking results. The Ekman (Ek) technique allows users to select six discrete emotions via button interaction, while the Scrollable-Ekman (SEk) technique extends this by allowing users to scale the intensity of the selected emotion. The Arousal-Valence (AV) technique offers nuanced control within a two-dimensional arousal-valence space. We evaluated these techniques against a baseline condition that synchronizes users' natural facial expressions, focusing on the expression of happiness, sadness, and anger. In most measurements, the Ek and SEk showed better results compared to the baseline and the AV techniques. Notably, the SEk technique was particularly effective in enhancing hedonic quality. During the free-flowing conversation, the most critical factor was the timely and well-synchronized coordination between speech and controlled facial expressions. Participant satisfaction also varied by usage style: those who tried to use the techniques continuously and naturally to mimic real-life communication reported lower satisfaction, while those who used them occasionally for playful or exaggerated expressions tended to report higher satisfaction.

Managing negative emotions through emotion regulation (ER) is key to mental well-being. While virtual reality (VR) shows promise for supporting ER, prior work has primarily focused on selfregulation. This paper introduces a virtual agent that helps users manage emotions through conversation-based ER strategies. We compared three conditions: no agent, an agent with non-supportive responses, and an agent with ER-supportive responses. Results showed that the ER-supportive agent significantly improved users' emotional states and overall experience. Building on this, we conducted a second experiment to examine how the agent's appearance (realistic vs. cartoon) and voice tone (emotional vs. neutral) affect ER. Results indicated that an emotional voice tone improved users' ability to regulate emotions. Although a realistic appearance did not directly improve ER, it increased users' trust and sense of social presence. This paper contributes to VR and human-agent interaction by demonstrating the potential of virtual agents to support ER and offering design implications for future ER-supportive agents.

Co-speech gestures are crucial for enriching both human-human and human-agent communications. Yet, the specific impacts of gesture size—especially when being generated by advanced data-driven techniques—remain underexplored. This study investigates how varying gesture sizes affect human-agent interactions across two distinct persuasive contexts (informational and emotional), with a focus on social outcomes such as persuasion and empathy. We conducted two controlled experiments, each involving 36 participants, comparing three gesture conditions: Minimal gesture, Small gesture, and Large gesture conditions. Experiment 1, set in an informational sales context, showed that small and large gestures significantly enhanced persuasive effectiveness, social presence, and communication quality compared to the minimal gesture condition, although no meaningful differences emerged between small and large gestures. In contrast, Experiment 2, situated in an emotionally charged context, revealed that larger gestures progressively amplified both persuasive impact and perceived empathy. These findings highlight that gesture size matters in emotionally intensive communications and the substantial social benefits of deep-learning techniques for gesture generation.

Embodied conversational agents (ECAs) capable of non-verbal behaviors have been developed to address the limitations of voice-only assistants, with research exploring their use in mixed and augmented reality (AR), suggesting they may soon interact with us more naturally in physical spaces. Traditionally, AI voice assistants are activated through wake-up keywords, and since they are invisible, their method of appearance has not been a concern. However, for ECAs in AR, the question of how they should enter the user's space when summoned remains underexplored. In this paper, we focused on the plausibility of ECAs' entering action into the user's field of view in AR. We analyzed its impact on user experience, concentrating on perceived social presence and co-presence of the agent. Three entrance styles were chosen for comparison: an obviously impossible one, a possible one, and an intermediate one, alongside a voice-only condition. We designed and conducted a within-subjects study with 38 participants. Our results indicated that while the plausibility of the action had less impact on functionality compared to the embodiment itself, it significantly affected social/co-presence. These findings highlight the importance of entrance design for future AR agent experiences.

In this paper, we introduce a novel Virtual Reality (VR) navigation method using gaze ray and hand, named RayHand navigation. It supports controlling navigation speed and direction by quickly indicating the initial direction using gaze and then using dexterous hand movement for controlling the speed and direction based on the relative position between the gaze ray and user's hand. We conducted a user study comparing our approach to the head-hand and torso-leaning-based navigation methods, and also evaluated their learning effect. The results showed that the RayHand and head-hand navigations were less physically demanding than the torso-leaning navigation, and the RayHand supported rich navigation experience with high hedonic quality and solved the issue of the user unintentionally stepping out from the designated interaction area. In addition, our approach showed a significant improvement over time with a learning effect.

In the realm of dyadic interactions, the ability to generate appropriate facial reactions is paramount for the conveyance of empathy and understanding. This paper introduces a novel framework that leverages the strengths of a diffusion model architecture, underpinned by a vector quantized variational autoencoder (VQ-VAE) to synthesize facial reactions that are contextually apt. We rigorously evaluate our model on the IEEE FG REACT2024 dataset, where it demonstrates superior performance, outshining baseline methods in terms of effectiveness. The results underscore the potential of our framework to enhance the fidelity of digital human interactions, paving the way for more nuanced and emotionally intelligent systems.

In this paper, we report on a research investigation exploring the application of a wearable, hands-free, low cost, AR audio-visual guidance system (HelpingHands) in the scenario of students learning clinical health procedures. The system enables health science students (nurses, doctors, and others) to learn and practice clinical procedures with real-time virtual guidance provided by a procedural expert (an instructor) located remotely at another site. User studies have been conducted to seek user requirements and evaluate the usability of the system. And the results demonstrated that HelpingHands is well-received by the end-users (students and instructors). This research contributes to the acquisition, development and performance of practical skills by students whilst undertaking work-integrated learning (WIL) placements in hospitals and other health care settings.

Recent routability research has exploited a machine learning (ML)-based modeling methodologies to consider various routability factors that are derived from placement solution. These factors are very related to the circuit characteristics (e.g., pin density, routing congestion, demand of routing resources, etc), and lack of circuit benchmarks in training can lead to poor predictability for ‘unseen’ circuit designs. In this paper, we propose a machine learning (ML) framework for early routability prediction modeling. The method includes a new artificial netlist generator (ANG) that generates an artificial gate-level netlist from the user-specified topology characteristics of synthetic circuit, even with real world circuit-like. In this framework, we exploit that ANG that supports obtaining ground truths for use in training ML-based model, the training dataset that have a wide range of topological characteristics provides strong ability to inference noisy, previous-unseen data. Compared to a design-specific training dataset [4] that is used for routability prediction modeling, we increase the test accuracy of binary classification (‘pass' or ‘fail’) on timing, DRC and routability by 6.3%, 8.6% and 6.6%, and reduce the generalization error [12] by as much as 87% compared to design-specific training dataset [4].

This paper describes the latest release of the DATC Robust Design Flow (RDF), RDF-2021, which has several key additions to expand its horizons. The Chisel/FIRRTL compiler is now part of DATC RDF, enabling support of recent hardware generator designs written in Chisel. Logic locking through RTL obfuscation, an updated ABC synthesis flow, and DFT support are other notable updates to the RDF. A Bookshelf-LEF/DEF converter powered by OpenDB is also added into DATC RDF's inventory as an enabler of robust benchmark conversion. We also describe efforts toward open metrics standards and datasets for machine learning (ML) applications and smart tuning of the design flow, as well as expansion of public analysis calibration data. Our paper closes with future research directions related to DATC's efforts.

In today's RTL-to-GDS flow domain, there is a lack of standards for reporting of design and tool metrics. Moreover, each tool or engine has its own set of parameters that can change outcomes and trade off PPA and other metrics. Thus, the study and optimization of impacts of parameter settings across the entire RTL- to-GDS tool chain has been largely ad hoc. In this paper, we first describe METRICS2.1, a proposed standard for RTL-to-GDS design tool and flow metrics. We then describe how data collected using a METRICS2.1 realization can be analyzed to give insight into flow tuning and fields of use for PPA optimization. Last, we discuss hyperparameter autotuning in the RTL-to-GDS flow. We present AutoTuner, which uses derivative-free optimization to handle challenges of non-differentiability and many local minima. An open repository based on METRICS2.1 has been established for sharing of reproducible, standardized metrics data, along with example implemented applications, to support academic and industrial research on machine learning for tool/flow tuning.

In advanced technology nodes, emerging 3-D integration technology is a promising “More Than Moore” lever for continued scaling of system capability and value. In the 3-D integrated circuit (3-D IC) implementation, the power delivery network (PDN) is crucial to meeting design specifications. However, determining the optimal PDN design is nontrivial. On the one hand, to meet the voltage (IR) drop requirement, a denser power mesh is desired. On the other hand, to meet the timing requirement, more routing resource is needed for signal routing. Moreover, additional competition between signal routing and power routing is caused by intertier vertical interconnects in 3-D IC. In this article, we propose a power delivery pathfinding methodology for emerging 3-D integration, which seeks to identify a “near-optimal” (or, very high quality) PDN for a given BEOL stack, vertical interconnection, and PDN specification. Compared with previous works, our methodology can explore richer solution spaces as it supports different PDN layer combinations and PDN layer configurations. We develop models for routability and worst IR drop to help reduce iterations between PDN design and circuit design in 3-D IC implementation. We present validations and demonstrate improvement in IR drop and routability with real design blocks in 28- and 14-nm foundry technology nodes.

We have proposed a proof of concept of a gaze window interface. A gaze window interface uses the user's gaze point to show the relevant content nearby the current gaze point. A system of a gaze window interface has been implemented that allows users to manage looking at multiple objects of interest on the screen while the system is responsive to the user's gaze points with relevant information shown in the gaze window. We also conducted user studies to investigate the effects of the interface on user performance and behaviors. In this paper, we report on a user study in which the gaze window was compared with a mouse window for supporting single user data entry tasks. We describe details of the study design and conduction and present the results.

Many researchers have studied various visual communication cues (e.g. pointer, sketching, and hand gesture) in Mixed Reality remote collaboration systems for real-world tasks. However, the effect of combining them has not been so well explored. We studied the effect of these cues in four combinations: hand only, hand + pointer, hand + sketch, and hand + pointer + sketch, with three problem tasks: Lego, Tangram, and Origami. The study results showed that the participants completed the task significantly faster and felt a significantly higher level of usability when the sketch cue is added to the hand gesture cue, but not with adding the pointer cue. Participants also preferred the combinations including hand and sketch cues over the other combinations. However, using additional cues (pointer or sketch) increased the perceived mental effort and did not improve the feeling of co-presence. We discuss the implications of these results and future research directions.

In advanced technology nodes, emerging die-to-wafer (D2W) integration technology is a promising "More Than Moore" lever for continued scaling of system capability and value. In D2W 3D IC implementation, the power delivery network (PDN) is crucial to meeting design specifications. However, determining the optimal PDN design is nontrivial. On the one hand, to meet the IR drop requirement, denser power mesh is desired. On the other hand, to meet the timing requirement for a high-utilization design, more routing resource should be available for signal routing. Moreover, additional competition between signal routing and power routing is caused by inter-tier vertical interconnects in 3D IC. In this paper, we propose a power delivery pathfinding methodology for emerging die-to-wafer integration, which seeks to identify an optimal or near-optimal PDN for a given design and PDN specification. Our pathfinding methodology exploits models for routability and worst IR drop, which helps reduce iterations between PDN design and circuit design in 3D IC implementation. We present validations with real design examples and a 28nm foundry technology.

In this paper, we explore the effect of showing a remote partner close to user gaze point in a teleconferencing system. We implemented a gaze following function in a teleconferencing system and investigate if this improves the user's feeling of emotional interdependence. We developed a prototype system that shows a remote partner close to the user's current gaze point and conducted a user study comparing it to a condition displaying the partner fixed in the corner of a screen. Our results showed that showing a partner close to their gaze point helped users feel a higher level of emotional interdependence. In addition, we compared the effect of our method between small and big displays, but there was no significant difference in the users' feeling of emotional interdependence even though the big display was preferred.

The power integrity of high-speed interfaces is an increasingly important issue in mobile memory systems. However, because of complicated design variations such as adjacent VDD domain coupling, conventional case-specific modeling is limited in analyzing trends in results from parametric variations. Moreover, conventional industrial methods can be simulated only after the design layout is completed and it requires a lot of back-annotation processes, which result in delayed delays time to market. In this paper, we propose a chip-package-PCB coanalysis methodology applied to our multi-domain high-speed memory system model with a current generation method. Our proposed parametric simulation model can analyze the tendency of power integrity results from variable sweeps and Monte Carlo simulations, and it shows a significantly reduced runtime compared to the conventional EDA methodology under JEDEC LPPDR4 environment.

Sharing and watching live 360 panorama video is available on modern social networking platforms, yet the communication is often a passive one-directional experience. This research investigates how to further improve live 360 panorama based remote collaborative experiences by adding Mixed Reality (MR) cues. SharedSphere is a wearable MR remote collaboration system that enriches a live captured immersive panorama based collaboration through MR visualisation of non-verbal communication cues (e.g., view awareness and gestures cues). We describe the design and implementation details of the prototype system, and report on a user study investigating how MR live panorama sharing affects the user's collaborative experience. The results showed that providing view independence through sharing live panorama enhances co-presence in collaboration, and the MR cues help users understanding each other. Based on the study results we discuss design implications and future research direction.

Incremental timing-driven placement (TDP) is one of the most crucial steps for timing closure in a physical design. The need for high-performance incremental TDP continues to grow, but prior studies have focused on optimizing only setup timing slacks, which can be easily stuck in local optima. In this paper, we present a useful skew methodology based on a maximum mean weight cycle (MMWC) approach in the incremental TDP. The proposed useful skew methodology finds an optimal clock latency for each flip-flop, and the clock latency is implemented by moving the flip-flops and/ or reassigning them to local clock buffers. With the proposed TDP method, we effectively reduce the early slack of ICCAD 2015 contest benchmarks, and achieve 124(%) and 78(%) of total quality score improvement compared to the 2015 contest winner, and early slack histogram compression (EHC) method, respectively. Moreover, with fewer iterations in the optimization, the runtime of our predictive useful skew method is an average of 7.4 times faster than an EHC method.

Layout pattern classification has been recently utilized in IC design. It clusters hotspot patterns for design-space analysis or yield optimization. In pattern classification, an optimal clustering is essential, as well as its runtime and accuracy. Within the research-oriented infrastructure used in the ICCAD 2016 contest, we have developed a fast metaheuristic for the pattern classification that utilizes the Greedy Randomized Adaptive Search Procedure (GRASP). Our proposed metaheuristic outperforms the best-reported results on all of the ICCAD 2016 benchmarks. In addition, we achieve up to a 50% cluster count reduction, and improve a runtime significantly compared to a commercial EDA tool provided in the ICCAD 2016 contest [1].

Among power dissipation components, leakage power has become more dominant with each successive technology node. Power-gating techniques have been widely used to reduce the standby leakage energy. In this work, we investigate a power-gating strategy for through-silicon via (TSV)-based 3D IC stacking structures. Power-gating control is becoming more complicated as more dies are stacked. We combine the on-chip PDN and TSV in a multilayered 3D IC to perform power-gating analysis of the static and dynamic voltage drops and in-rush current. Then, we propose a novel power-gating strategy that optimizes the in-rush current profile, subject to the voltage-drop constraints. Our power-gating strategy provides a minimal wake-up latency such that the voltage noise safety margins are not violated. In addition, the layer dependency of the 3D IC on the power gating is analyzed in terms of the wake-up time reduction. We achieve an average wake-up time reduction of 43% for all cases with our adaptive power-gating method that exploits location (or layer) information regarding the aggressors in a 3D IC. A tapered TSV architecture based on the layer dependency has been analyzed; it exhibits up to 18% wake-up time reduction compared to that of circuits with uniform TSVs.

For applications related to human, such as Internet of Things (loT) and wearable devices, near threshold voltage (NTV) technology has been proposed for the trade-off between performance and energy consumption. However, errorresilient techniques are required in the circuits to improve reliability of the NTV operation. In this paper, we propose a low-overhead error-resilient system and a design flow for NTV operations. We use a new monitoring circuit, which can detect timing errors and find an optimal operation point of the system. Also, we propose two different methodologies, which are slack-based methodology and sensitivity-based methodology. From the proposed monitoring system and the sensitivitybased sorting algorithm, benchmark results show that the optimal designs provide up to 46% monitoring area reduction maintaining similar error detection ability of the conventional error-resilient design.

Mobile videoconferencing is increasingly being used to bring remote friends or family along to an activity happening outside the home, such as shopping or visiting a tourist attraction. We explored how including contextual information of the event, in addition to audio and video of the person at the event, impacts the shared experience. We studied three kinds of information: a map showing the position of the person at the activity, a second live video showing what was in front of that person, and periodic high quality images showing what was in front of the person. We carried out a field study with twelve pairs of participants, where one participant (the nomad) was at a self-selected activity while the other (the couch potato) joined the activity from our living room lab. The study results show that including contextual information significantly improved connectedness and the sense of presence for both participants. Each type of contextual information offered unique benefits. The map was used for orientation and to provide directions, the live video for "do you see this" moments and to maintain a sense of liveliness, and the periodic images for "did you see that" moments and to see greater detail. Together they led to smooth view negotiation, activity input from the couch potato, and high levels of engagement.

Video conferencing is becoming more widely used in areas other than face-to-face conversation, such as sharing real world experience with remote friends or family. In this paper we explore how adding augmented visual communication cues can improve the experience of sharing remote task space and collaborating together. We developed a prototype system that allows users to share live video view of their task space taken on a Head Mounted Display (HMD) or Handheld Display (HHD), and communicate through not only voice but also using augmented pointer or annotations drawn on the shared view. To explore the effect of having such an interface for remote collaboration, we conducted a user study comparing three video-conferencing conditions with different combination of communication cues: (1) voice only, (2) voice + pointer, and (3) voice + annotation. The participants used our remote collaboration system to share a parallel experience of puzzle solving in the user study, and we found that adding augmented visual cues significantly improved the sense of being together. The pointer was the most preferred additional cue by users for parallel experience, and there were different states of the users' behavior found in remote collaboration.

In this research, we explore using pointing and drawing in a remote collaboration system. Our application allows a local user with a tablet to communicate with a remote expert on a desktop computer. We compared performance in four conditions: (1) Pointers on Still Image, (2) Pointers on Live Video, (3) Annotation on Still Image, and (4) Annotation on Live Video. We found that using drawing annotations would require fewer inputs on an expert side, and would require less cognitive load on the local worker side. In a follow-on study we compared the conditions (2) and (4) using a more complicated task. We found that pointing input requires good verbal communication to be effective and that drawing annotations need to be erased after completing each step of a task.

In this research, we explore how different types of augmented gesture communication cues can be used under different view sharing techniques in a remote collaboration system. In a pilot study, we compared four conditions: (1) Pointers on Still Image, (2) Pointers on Live Video, (3) Annotation on Still Image, and (4) Annotation on Live Video. Through this study, we found three results. First, users collaborate more efficiently using annotation cues than pointer cues for communicating object position and orientation information. Second, live video becomes more important when quick feedback is needed. Third, the type of gesture cue has more influence on performance and user preference than the type of view sharing method.

Home network providers have many issues to resolve in providing home network services with an expandable, reliable, flexible, and low-cost structure to accommodate the expanding market environment. Current client-server systems have various problems, such as complexity and high costs to provide home network services. However, these problems can be simply solved by employing the P2P communication terminal that supports access of distributed resources to provide the functions that the current SIP-based network devices perform. Because diverse terminals in a home network access through networks, partitioning network domains with home gateways to manage and applying the network-based PMIPv6 (Proxy Mobile IPv6) technology that considers mobility of terminals would also help to create a more efficient home network structure. This proposed P2P-SIP architecture is very efficient with outstanding expandability to support the various home networks in a region while reducing maintenance costs.

In this paper, we present a new phrase break prediction method that integrates second-order information into general maximum entropy model. The phrase break prediction problem was mapped into a classification problem in our research. The features we used for the prediction of phrase breaks are of several layers such as local features (part-of-speech (POS) tags, a lexicon, lengths of eojeols 1 and location of juncture in the sentence), global features (chunk label derived from a eojeol parse tree) and second-order features (distance probability of previous and next phrase break). These three features were combined and used in the experiments, and we were able to generate good performance especially in the major phrase break prediction. Index Terms: phrase break, prosodic phrasing, speech synthesis, ToBI

In this paper, we describe a method for automatically extracting grapheme-to-phoneme conversion rules directly from the transcription of speech synthesis database and introduce a weighted score and jamo * similarity to overcome the rule application difficulties. We make a structured rule tree by rule pruning and rule association, and can eliminate most of the rules with almost no decrease of the performance. Our system achieves over 99.5 percent of phoneme-level accuracy and this performance is easily achievable even with the small amount of training data. Index Terms: grapheme-to-phoneme conversion, letter-tosound rule, text-to-speech system