Huang

Qiuhua Huang, Renke Huang, Rui Fan et al.

Transmission and distribution dynamic co-simulation is a practical and effective approach to leverage existing simulation tools for transmission and distribution systems to simulate dynamic stability and performance of transmission and distribution systems in a systematic manner. Given that these tools are developed as stand-alone programs and there are inherent differences between them, interface techniques become critical to bridge them. Two important unsolved questions are: 1) which interface technique is better and should be used, and 2) how the modeling and simulation capabilities in these tools that are available and can be exploited for co-simulation should be considered when selecting an interface technique. To address these questions, this paper presents a comparative study for different interface techniques that can be employed for T and D dynamic co-simulation. The study provides insights into the pros and cons of each interface technique, and helps researchers make informed decisions on choosing the interface techniques.

Yuming, Huang, Yao Liu et al.

Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing the target's training cohort cannot independently verify it. Anchoring validity to a single human-rater consensus does not extend to capabilities where humans themselves disagree. We propose a replication-first paradigm: instead of anchoring on one rater group, we certify the instrument via four orthogonal properties -- reliability across K runs, cross-instrument replication across architecturally distinct judges, historical-footprint calibration via judges from earlier training cohorts, and pre-registered prediction. We test it on emotional accompaniment by letting the rubric self-evolve data-driven across iterations: the dimensions are not pre-stipulated and the procedure stabilizes to a 9-dimension set. Pre-registration applies to 10 falsifiable hypotheses and 11 forward predictions, committed before any test data was collected. Applied to 49 models across 8 families, the paradigm surfaces what aggregate scores hide. On advice-restraint -- whether a model refrains from giving unsolicited solutions in empathic contexts -- gpt-5 falls 1.87 points from gpt-4.1 and Opus-4.7 falls 0.629 from Opus-4.6, while aggregate scores stay flat. The regression survives three user-proxy swaps (95% of magnitude), replicates across a 5-family judge stack and a 17-month cohort gap, and persists on 74 held-out real ESConv conversations (rho in [0.749, 0.850]); the instrument reaches ordinal Krippendorff alpha = 0.91. As a by-product, the paradigm acts as a saturation-source diagnostic, separating instrumental ceilings (breakable by rubric refinement) from structural ceilings (needing scenario or roster intervention).

Lingling Fan, Ali Yazdanpanah, Yunzhi Cheng et al.

In 2024, Texas operators observed 23-Hz oscillations in real power measurements close to a large electronic load (LEL). Oscillations emerged when the load's power consumption reached approximately 320 MW level and subsided as the active power demand decreased. The paper aims to analyze the event and reproduce the oscillations using electromagnetic transient (EMT) simulations. In the first stage, a representative feedback system is developed, and frequency-domain analysis is conducted to examine the phenomenon and identify its key influencing factors. Next, detailed EMT simulations are performed to further validate the proposed analytical approach. The results show that the feedback system effectively captures and characterizes the critical features of the 23-Hz oscillation incident. In addition, the EMT simulations successfully reproduce the real-world event, with the simulated results closely matching the fault recorder data.

Elaine Kong, Kuo-Ting, Huang et al.

The use of Artificial Intelligence (AI) in healthcare, including in caring for cancer survivors, has gained significant interest. However, gaps remain in our understanding of how such AI systems can provide care, especially for ethnic and racial minority groups who continue to face care disparities. Through interviews with six cancer survivors, we identify critical gaps in current healthcare systems such as a lack of personalized care and insufficient cultural and linguistic accommodation. AI, when applied to care, was seen as a way to address these issues by enabling real-time, culturally aligned, and linguistically appropriate interactions. We also uncovered concerns about the implications of AI-driven personalization, such as data privacy, loss of human touch in caregiving, and the risk of echo chambers that limit exposure to diverse information. We conclude by discussing the trade-offs between AI-enhanced personalization and the need for structural changes in healthcare that go beyond technological solutions, leading us to argue that we should begin by asking, ``Why personalization?''

Wenqian Ye, Luyang Jiang, Eric Xie et al.

Back in the early 20th century, a horse named Hans appeared to perform arithmetic and other intellectual tasks during exhibitions in Germany, while it actually relied solely on involuntary cues in the body language from the human trainer. Modern machine learning models are no different. These models are known to be sensitive to spurious correlations between non-essential features of the inputs (e.g., background, texture, and secondary objects) and the corresponding labels. Such features and their correlations with the labels are known as "spurious" because they tend to change with shifts in real-world data distributions, which can negatively impact the model's generalization and robustness. In this paper, we provide a comprehensive survey of this emerging issue, along with a fine-grained taxonomy of existing state-of-the-art methods for addressing spurious correlations in machine learning models. Additionally, we summarize existing datasets, benchmarks, and metrics to facilitate future research. The paper concludes with a discussion of the broader impacts, the recent advancements, and future challenges in the era of generative AI, aiming to provide valuable insights for researchers in the related domains of the machine learning community.

Anca-Simona Horvath, Cristian Tosa, Simai et al.

Urban to rural migration is a less-researched phenomenon compared to its counterpart: rural to urban migration. In parts of Europe, an increasing number of people living in big urban centers within the country, or moving from other countries decide to relocate to rural areas. In this paper, we examine this phenomenon by analysing content posted on TikTok that documents this transition. We collected a corpus of 901 videos posted until late 2025, documenting urban to rural migration in Romania, under three hashtags, which have collectively been played a total of 24 million times at the time when we gathered the dataset. We analyse this corpus both quantitatively and qualitatively and discuss our findings through the lens of digital rurality - a theory based on Harvey's and Soja's spatial triad, applied to rural spaces, and based on the role of digital technologies as (re-)mediators of everyday lived experience. Specifically, we analyze the corpus as: (a) digital rural localities, (b) formal representations of the digital rural, and (c) everyday lives of the digital rural. We find that (a) Social media platforms enable new forms of paid labor that sometimes involve the commodification of the self in rural areas, although many of the creators we analyze do not explicitly acknowledge this with their audiences. (b) The digital rural gains new forms of representation, and rural areas in remote Romania are highly data-rich across TikTok. (c) The everyday lives represented through the digital rural are sometimes idealized or romanticised. However, they serve as promoters for tourism and are used as sites to document and discuss a variety of topics including giving ample health advice, typically by non-specialists and sometimes criticizing Western medicine, expressing and promoting religious and political views but also acting as forms of general self-expression.

Boyuan Chen, Sitong Fang, Jiaming Ji et al.

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

Chien-Fu, Huang, Katherine Sieg et al.

Controlling defects in semiconductor processes is important for maintaining yield, improving production cost, and preventing time-dependent critical component failures. Electron beam-based imaging has been used as a tool to survey wafers in the line and inspect for defects. However, manual classification of images for these nano-scale defects is limited by time, labor constraints, and human biases. In recent years, deep learning computer vision algorithms have shown to be effective solutions for image-based inspection applications in industry. This work proposes application of vision transformer (ViT) neural networks for automatic defect classification (ADC) of scanning electron microscope (SEM) images of wafer defects. We evaluated our proposed methods on 300mm wafer semiconductor defect data from our fab in IBM Albany. We studied 11 defect types from over 7400 total images and investigated the potential of transfer learning of DinoV2 and semi-supervised learning for improved classification accuracy and efficient computation. We were able to achieve classification accuracies of over 90% with less than 15 images per defect class. Our work demonstrates the potential to apply the proposed framework for a platform agnostic in-house classification tool with faster turnaround time and flexibility.

Chinmay Shah, Aaron Fleming, Varun Nalam et al.

Existing robotic lower-limb prostheses use autonomous control to address cyclic, locomotive tasks, but they are inadequate to operate the prosthesis for daily activities that are non-cyclic and unpredictable. To address this challenge, this study aims to design a novel electromyography (EMG)-driven musculoskeletal model for volitional control of a robotic ankle-foot prosthesis. This controller places the user in continuous control of the device, allowing them to freely manipulate the prosthesis behavior at will. The Hill-type muscle model was used to model a dorsiflexor and a plantarflexor, which functioned around a virtual ankle joint. The model parameters were determined by fitting the model prediction to the experimental data collected from an able-bodied subject. EMG signals recorded from ankle agonist and antagonist muscle pair were used to activate the virtual muscle models. This model was validated via offline simulations and real-time prosthesis control. Additionally, the feasibility of the proposed prosthesis control on assisting the user's functional tasks was demonstrated. The present control may further improve the function of robotic prosthesis for supporting versatile activities in individuals with lower-limb amputations.

Ashwin De Silva, Rahul Ramesh, Lyle Ungar et al.

Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

Rajeev Rikhye, Quan Wang, Qiao Liang et al.

In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic speech recognition (ASR) model and a text-independent speaker verification model. To address the challenge of detecting these keyphrases under various noisy conditions, a speaker separation model is added to the feature frontend of the speaker verification model, and an adaptive noise cancellation (ANC) algorithm is included to exploit cross-microphone noise coherence. Our experiments show that the text-independent speaker verification model largely reduces the false triggering rate of the keyphrase detection, while the speaker separation model and adaptive noise cancellation largely reduce false rejections.

Ruofan Wu, Zhikai Yao, Jennie Si et al.

We address a state-of-the-art reinforcement learning (RL) control approach to automatically configure robotic prosthesis impedance parameters to enable end-to-end, continuous locomotion intended for transfemoral amputee subjects. Specifically, our actor-critic based RL provides tracking control of a robotic knee prosthesis to mimic the intact knee profile. This is a significant advance from our previous RL based automatic tuning of prosthesis control parameters which have centered on regulation control with a designer prescribed robotic knee profile as the target. In addition to presenting the complete tracking control algorithm based on direct heuristic dynamic programming (dHDP), we provide an analytical framework for the tracking controller with constrained inputs. We show that our proposed tracking control possesses several important properties, such as weight convergence of the learning networks, Bellman (sub)optimality of the cost-to-go value function and control input, and practical stability of the human-robot system under input constraint. We further provide a systematic simulation of the proposed tracking control using a realistic human-robot system simulator, the OpenSim, to emulate how the dHDP enables level ground walking, walking on different terrains and at different paces. These results show that our proposed dHDP based tracking control is not only theoretically suitable, but also practically useful.

Ruofan Wu, Minhan Li, Zhikai Yao et al.

Automatically configuring a robotic prosthesis to fit its user's needs and physical conditions is a great technical challenge and a roadblock to the adoption of the technology. Previously, we have successfully developed reinforcement learning (RL) solutions toward addressing this issue. Yet, our designs were based on using a subjectively prescribed target motion profile for the robotic knee during level ground walking. This is not realistic for different users and for different locomotion tasks. In this study for the first time, we investigated the feasibility of RL enabled automatic configuration of impedance parameter settings for a robotic knee to mimic the intact knee motion in a co-adapting environment. We successfully achieved such tracking control by an online policy iteration. We demonstrated our results in both OpenSim simulations and two able-bodied (AB) subjects.

Jihyeon Lee, Joseph Z. Xu, Kihyuk Sohn et al.

To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which indicate what buildings and population centers have been most affected. Recent research combines machine learning with remote sensing to automatically extract such information from satellite imagery, reducing manual labor and turn-around time. A major impediment to using machine learning methods in real disaster response scenarios is the difficulty of obtaining a sufficient amount of labeled data to train a model for an unfolding disaster. This paper shows a novel application of semi-supervised learning (SSL) to train models for damage assessment with a minimal amount of labeled data and large amount of unlabeled data. We compare the performance of state-of-the-art SSL methods, including MixMatch and FixMatch, to a supervised baseline for the 2010 Haiti earthquake, 2017 Santa Rosa wildfire, and 2016 armed conflict in Syria. We show how models trained with SSL methods can reach fully supervised performance despite using only a fraction of labeled data and identify areas for further improvements.

Xikai Tu, Minhan Li, Ming Liu et al.

Robotic exoskeletons are exciting technologies for augmenting human mobility. However, designing such a device for seamless integration with the human user and to assist human movement still is a major challenge. This paper aims at developing a novel data-driven solution framework based on reinforcement learning (RL), without first modeling the human-robot dynamics, to provide optimal and adaptive personalized torque assistance for reducing human efforts during walking. Our automatic personalization solution framework includes the assistive torque profile with two control timing parameters (peak and offset timings), the least square policy iteration (LSPI) for learning the parameter tuning policy, and a cost function based on transferred work ratio. The proposed controller was successfully validated on a healthy human subject to assist unilateral hip extension in walking. The results showed that the optimal and adaptive RL controller as a new approach was feasible for tuning assistive torque profile of the hip exoskeleton that coordinated with human actions and reduced activation level of hip extensor muscle in human.

Xiang Gao, Jennie Si, Yue Wen et al.

We are motivated by the real challenges presented in a human-robot system to develop new designs that are efficient at data level and with performance guarantees such as stability and optimality at systems level. Existing approximate/adaptive dynamic programming (ADP) results that consider system performance theoretically are not readily providing practically useful learning control algorithms for this problem; and reinforcement learning (RL) algorithms that address the issue of data efficiency usually do not have performance guarantees for the controlled system. This study fills these important voids by introducing innovative features to the policy iteration algorithm. We introduce flexible policy iteration (FPI), which can flexibly and organically integrate experience replay and supplemental values from prior experience into the RL controller. We show system level performances including convergence of the approximate value function, (sub)optimality of the solution, and stability of the system. We demonstrate the effectiveness of the FPI via realistic simulations of the human-robot system. It is noted that the problem we face in this study may be difficult to address by design methods based on classical control theory as it is nearly impossible to obtain a customized mathematical model of a human-robot system either online or offline. The results we have obtained also indicate the great potential of RL control to solving realistic and challenging problems with high dimensional control inputs.

Sheng-Yeh Chen, Chao-Chun Hsu, Chuan-Chun Kuo et al.

Feeling emotion is a critical characteristic to distinguish people from machines. Among all the multi-modal resources for emotion detection, textual datasets are those containing the least additional information in addition to semantics, and hence are adopted widely for testing the developed systems. However, most of the textual emotional datasets consist of emotion labels of only individual words, sentences or documents, which makes it challenging to discuss the contextual flow of emotions. In this paper, we introduce EmotionLines, the first dataset with emotions labeling on all utterances in each dialogue only based on their textual content. Dialogues in EmotionLines are collected from Friends TV scripts and private Facebook messenger dialogues. Then one of seven emotions, six Ekman's basic emotions plus the neutral emotion, is labeled on each utterance by 5 Amazon MTurkers. A total of 29,245 utterances from 2,000 dialogues are labeled in EmotionLines. We also provide several strong baselines for emotion detection models on EmotionLines in this paper.

Chieh-Yang Huang, Ting-Hao, Huang et al.

Instant messaging is one of the major channels of computer mediated communication. However, humans are known to be very limited in understanding others' emotions via text-based communication. Aiming on introducing emotion sensing technologies to instant messaging, we developed EmotionPush, a system that automatically detects the emotions of the messages end-users received on Facebook Messenger and provides colored cues on their smartphones accordingly. We conducted a deployment study with 20 participants during a time span of two weeks. In this paper, we revealed five challenges, along with examples, that we observed in our study based on both user's feedback and chat logs, including (i)the continuum of emotions, (ii)multi-user conversations, (iii)different dynamics between different users, (iv)misclassification of emotions and (v)unconventional content. We believe this discussion will benefit the future exploration of affective computing for instant messaging, and also shed light on research of conversational emotion sensing.

Ting-Hao, Huang, Francis Ferraro et al.

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.

Xiangming Meng, Sheng Wu, Linling Kuang et al.

We consider the problem of recovering clustered sparse signals with no prior knowledge of the sparsity pattern. Beyond simple sparsity, signals of interest often exhibits an underlying sparsity pattern which, if leveraged, can improve the reconstruction performance. However, the sparsity pattern is usually unknown a priori. Inspired by the idea of k-nearest neighbor (k-NN) algorithm, we propose an efficient algorithm termed approximate message passing with nearest neighbor sparsity pattern learning (AMP-NNSPL), which learns the sparsity pattern adaptively. AMP-NNSPL specifies a flexible spike and slab prior on the unknown signal and, after each AMP iteration, sets the sparse ratios as the average of the nearest neighbor estimates via expectation maximization (EM). Experimental results on both synthetic and real data demonstrate the superiority of our proposed algorithm both in terms of reconstruction performance and computational complexity.

Francis Ferraro, Nasrin Mostafazadeh, Ting-Hao et al.

Integrating vision and language has long been a dream in work on artificial intelligence (AI). In the past two years, we have witnessed an explosion of work that brings together vision and language from images to videos and beyond. The available corpora have played a crucial role in advancing this area of research. In this paper, we propose a set of quality metrics for evaluating and analyzing the vision & language datasets and categorize them accordingly. Our analyses show that the most recent datasets have been using more complex language and more abstract concepts, however, there are different strengths and weaknesses in each.