Search

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai., Comment: 25 pages, 6 figures

While CLIP has significantly advanced multimodal understanding by bridging vision and language, the inability to grasp negation - such as failing to differentiate concepts like "parking" from "no parking" - poses substantial challenges. By analyzing the data used in the public CLIP model's pre-training, we posit this limitation stems from a lack of negation-inclusive data. To address this, we introduce data generation pipelines that employ a large language model (LLM) and a multimodal LLM to produce negation-inclusive captions. Fine-tuning CLIP with data generated from our pipelines, we develop NegationCLIP, which enhances negation awareness while preserving the generality. Moreover, to enable a comprehensive evaluation of negation understanding, we propose NegRefCOCOg-a benchmark tailored to test VLMs' ability to interpret negation across diverse expressions and positions within a sentence. Experiments on various CLIP architectures validate the effectiveness of our data generation pipelines in enhancing CLIP's ability to perceive negation accurately. Additionally, NegationCLIP's enhanced negation awareness has practical applications across various multimodal tasks, demonstrated by performance gains in text-to-image generation and referring image segmentation.

Understanding the ability of humans to use objects is crucial for AI to improve daily life. Existing studies for learning such ability focus on human-object patterns (e.g., contact, spatial relation, orientation) in static situations, and learning Human-Object Interaction (HOI) patterns over time (i.e., movement of human and object) is relatively less explored. In this paper, we introduce a novel type of affordance named Dynamic Affordance. For a given input 3D object mesh, we learn dynamic affordance which models the distribution of both (1) human motion and (2) human-guided object pose during interactions. As a core idea, we present a method to learn the 3D dynamic affordance from synthetically generated 2D videos, leveraging a pre-trained video diffusion model. Specifically, we propose a pipeline that first generates 2D HOI videos from the 3D object and then lifts them into 3D to generate 4D HOI samples. Once we generate diverse 4D HOI samples on various target objects, we train our DAViD, where we present a method based on the Low-Rank Adaptation (LoRA) module for pre-trained human motion diffusion model (MDM) and an object pose diffusion model with human pose guidance. Our motion diffusion model is extended for multi-object interactions, demonstrating the advantage of our pipeline with LoRA for combining the concepts of object usage. Through extensive experiments, we demonstrate our DAViD outperforms the baselines in generating human motion with HOIs., Comment: Project Page: https://snuvclab.github.io/david/

At two-thirds the weight of aluminum, magnesium alloys have the potential to significantly reduce the fuel consumption of transportation vehicles. These advancements depend on our ability to optimize the desirable versus undesirable effects of deformation twins: three dimensional (3D) microstructural domains that form under mechanical stresses. Previously only characterized using surface or thin-film measurements, here, we present the first 3D in-situ characterization of deformation twinning inside an embedded grain over mesoscopic fields of view using dark-field X-ray microscopy supported by crystal plasticity finite element analysis. The results reveal the important role of triple junctions on twin nucleation, that twin growth behavior is irregular and can occur in several directions simultaneously, and that twin-grain and twin-twin junctions are the sites of localized dislocation accumulation, a necessary precursor to crack initiation.

Large language models (LLMs) have recently emerged as powerful tools, finding many medical applications. LLMs' ability to coalesce vast amounts of information from many sources to generate a response-a process similar to that of a human expert-has led many to see potential in deploying LLMs for clinical use. However, medicine is a setting where accurate reasoning is paramount. Many researchers are questioning the effectiveness of multiple choice question answering (MCQA) benchmarks, frequently used to test LLMs. Researchers and clinicians alike must have complete confidence in LLMs' abilities for them to be deployed in a medical setting. To address this need for understanding, we introduce a knowledge graph (KG)-based method to evaluate the biomedical reasoning abilities of LLMs. Essentially, we map how LLMs link medical concepts in order to better understand how they reason. We test GPT-4, Llama3-70b, and PalmyraMed-70b, a specialized medical model. We enlist a panel of medical students to review a total of 60 LLM-generated graphs and compare these graphs to BIOS, a large biomedical KG. We observe GPT-4 to perform best in our human review but worst in our ground truth comparison; vice-versa with PalmyraMed, the medical model. Our work provides a means of visualizing the medical reasoning pathways of LLMs so they can be implemented in clinical settings safely and effectively., Comment: Findings paper presented at Machine Learning for Health (ML4H) symposium 2024, December 15-16, 2024, Vancouver, Canada, 19 pages

To ensure coherent signal processing across distributed Access Points (APs) in Cell-Free Massive Multiple-Input Multiple-Output (CF-mMIMO) systems, a fronthaul connection between the APs and a Central Processor (CP) is imperative. We consider a fronthaul network employing parallel radio stripes. In this system, APs are grouped into multiple segments where APs within each segment are sequentially connected through a radio stripe. This fronthaul topology strikes a balance between standard star and bus topologies, which deploy parallel or serial connections of all APs. Our focus lies in designing the uplink signal processing for a CF-mMIMO system with parallel radio stripes. We tackle the challenge of finite-capacity fronthaul links by addressing the design of In-Network Processing (INP) strategies at APs. These strategies involve linearly combining received signals and compressing the combining output for fronthaul transmission, aiming to maximize the sum-rate performance. Given the high complexity and the stringent requirement for global Channel State Information (CSI) in jointly optimizing INP strategies across all APs, we propose an efficient sequential design approach. Numerical results demonstrate that the proposed sequential INP design achieves a sum-rate gain of up to 82.92% compared to baseline schemes., Comment: accepted for publication in IEEE Access

With the growing demand to fit fine-grained user intents, faceted query-by-example (QBE), which retrieves similar documents conditioned on specific facets, has gained recent attention. However, prior approaches mainly depend on document-level comparisons using basic indicators like citations due to the lack of facet-level relevance datasets; yet, this limits their use to citation-based domains and fails to capture the intricacies of facet constraints. In this paper, we propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets. We automatically decompose documents into facet units and generate (ir)relevant pairs by leveraging LLMs' intrinsic distinguishing capabilities; then, dynamically recomposing the units leads to facet-wise relevance-informed document pairs. Our modularization eliminates the need for pre-defined facet knowledge or labels. Further, to prove the FaBle's efficacy in a new domain beyond citation-based scientific paper retrieval, we release a benchmark dataset for educational exam item QBE. FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.

Recently, large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, controllable summarization with LLMs remains underexplored, limiting their ability to generate summaries that align with specific user preferences. In this paper, we first investigate the capability of LLMs to control diverse attributes, revealing that they encounter greater challenges with numerical attributes, such as length and extractiveness, compared to linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in explaining errors in the previous output. Based on this reflection, the model generates a well-adjusted summary. As a result, by allowing the model to reflect on its misalignment, we generate summaries that satisfy the desired attributes in surprisingly fewer iterations than other iterative methods solely using LLMs.

This paper presents an approach to joint wireless and computing resource management in slice-enabled metaverse networks, addressing the challenges of inter-slice and intra-slice resource allocation in the presence of in-network computing. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem and derive an optimal solution using standard optimization techniques. Through extensive simulations, we demonstrate that our proposed method significantly improves system performance by effectively balancing the allocation of radio and computing resources across multiple slices. Our approach outperforms existing benchmarks, particularly in scenarios with high user demand and varying computational tasks.

A smooth diamond film, characterized by exceptional thermal conductivity, chemical stability, and optical properties, is highly suitable for a wide range of advanced applications. However, achieving uniform film quality presents a significant challenge for the CVD method due to non-uniformities in microwave distribution, electric fields, and the densities of reactive radicals during deposition processes involving $CH_4$ and $H_2$ precursors. Here, we systematically investigate the effects of microwave power and chamber pressure on surface roughness, crystalline quality, and the uniformity of diamond films. These findings provide valuable insights into the production of atomically smooth, high-quality diamond films with enhanced uniformity. By optimizing deposition parameters, we achieved a root-mean-square (RMS) surface roughness of 2 nm, comparable to high-pressure, high-temperature (HPHT) diamond substrates. Moreover, these conditions facilitated the formation of a pure single-crystal diamond phase, confirmed by the absence of contamination peaks in the Raman spectra

Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often struggle to filter out irrelevant documents within the context, and their performance is sensitive to the position of supporting documents within that context. In this paper, we identify an additional challenge: LLMs' performance is also sensitive to the order in which the supporting documents are presented. We refer to this as the misordered context problem. To address this issue, we propose a simple yet effective method called context repetition (CoRe), which involves prompting the model by repeatedly presenting the context to ensure the supporting documents are presented in the optimal order for the model. Using CoRe, we improve the F1 score by up to 30%p on multi-hop QA tasks and increase accuracy by up to 70%p on a synthetic task. Additionally, CoRe helps mitigate the well-known "lost-in-the-middle" problem in LLMs and can be effectively combined with retrieval-based approaches utilizing Chain-of-Thought (CoT) reasoning.

Model updating of engineering systems inevitably involves handling both aleatory or inherent randomness and epistemic uncertainties or uncertainities arising from a lack of knowledge or information about the system. Addressing these uncertainties poses significant challenges, particularly when data and simulations are limited. This study proposes a novel latent space-based method for stochastic model updating that leverages limited data to effectively quantify uncertainties in engineering applications. By extending the latent space-based approach to multiobservation and multisimulation frameworks, the proposed method circumvents the need for probability estimations at each iteration of MCMC, relying instead on an amortized probabilistic model trained using a variational autoencoder (VAE). This method was validated through numerical experiments on a two-degree-of-freedom shear spring model, demonstrating superior efficiency and accuracy compared to existing methods in terms of uncertainty quantification (UQ) metrics, such as Bhattacharyya and Euclidean distances. Moreover, the applicability of the method to time-series data was verified using the model calibration problem of the NASA UQ Challenge 2019. The results underscore the potential of the latent space-based method in practical engineering applications, providing a robust framework for uncertainty quantification with fewer data requirements, and demonstrating its effectiveness in handling high-dimensional data.

Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback. Like typical AES systems, multi-trait AES employs the quadratic weighted kappa (QWK) to measure agreement with human raters, aligning closely with the rating schema; however, its non-differentiable nature prevents its direct use in neural network training. In this paper, we propose Scoring-aware Multi-reward Reinforcement Learning (SaMRL), which integrates actual evaluation schemes into the training process by designing QWK-based rewards with a mean-squared error penalty for multi-trait AES. Existing reinforcement learning (RL) applications in AES are limited to classification models despite associated performance degradation, as RL requires probability distributions; instead, we adopt an autoregressive score generation framework to leverage token generation probabilities for robust multi-trait score predictions. Empirical analyses demonstrate that SaMRL facilitates model training, notably enhancing scoring of previously inferior prompts., Comment: EMNLP 2024

The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable concepts to enhance interpretability. However, existing CBMs face challenges due to deterministic concept encoding and reliance on inconsistent concepts, leading to inaccuracies. We propose EQ-CBM, a novel framework that enhances CBMs through probabilistic concept encoding using energy-based models (EBMs) with quantized concept activation vectors (qCAVs). EQ-CBM effectively captures uncertainties, thereby improving prediction reliability and accuracy. By employing qCAVs, our method selects homogeneous vectors during concept encoding, enabling more decisive task performance and facilitating higher levels of human intervention. Empirical results using benchmark datasets demonstrate that our approach outperforms the state-of-the-art in both concept and task accuracy., Comment: Accepted by ACCV 2024

Knowledge Graph-to-Text (G2T) generation involves verbalizing structured knowledge graphs into natural language text. Recent advancements in Pretrained Language Models (PLMs) have improved G2T performance, but their effectiveness depends on datasets with precise graph-text alignment. However, the scarcity of high-quality, general-domain G2T generation datasets restricts progress in the general-domain G2T generation research. To address this issue, we introduce Wikipedia Ontology-Free Graph-text dataset (WikiOFGraph), a new large-scale G2T dataset generated using a novel method that leverages Large Language Model (LLM) and Data-QuestEval. Our new dataset, which contains 5.85M general-domain graph-text pairs, offers high graph-text consistency without relying on external ontologies. Experimental results demonstrate that PLM fine-tuned on WikiOFGraph outperforms those trained on other datasets across various evaluation metrics. Our method proves to be a scalable and effective solution for generating high-quality G2T data, significantly advancing the field of G2T generation., Comment: 18 pages, 9 figures

In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from human feedback. However, existing PbRL methods have limitations as they often overlook the second-order preference that indicates the relative strength of preference. In this paper, we propose Listwise Reward Estimation (LiRE), a novel approach for offline PbRL that leverages second-order preference information by constructing a Ranked List of Trajectories (RLT), which can be efficiently built by using the same ternary feedback type as traditional methods. To validate the effectiveness of LiRE, we propose a new offline PbRL dataset that objectively reflects the effect of the estimated rewards. Our extensive experiments on the dataset demonstrate the superiority of LiRE, i.e., outperforming state-of-the-art baselines even with modest feedback budgets and enjoying robustness with respect to the number of feedbacks and feedback noise. Our code is available at https://github.com/chwoong/LiRE, Comment: 21 pages, ICML 2024

A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe that language models exhibit a negative bias in the binary decisions of complex reasoning tasks. Based on our observations and the rationale about attention-based model dynamics, we propose a negative attention score (NAS) to systematically and quantitatively formulate negative bias. Based on NAS, we identify attention heads that attend to negative tokens provided in the instructions as answer candidate of binary decisions, regardless of the question in the prompt, and validate their association with the negative bias. Additionally, we propose the negative attention score alignment (NASA) method, which is a parameter-efficient fine-tuning technique to address the extracted negatively biased attention heads. Experimental results from various domains of reasoning tasks and large model search space demonstrate that NASA significantly reduces the gap between precision and recall caused by negative bias while preserving their generalization abilities. Our codes are available at \url{https://github.com/ysw1021/NASA}.

This paper presents a cooperative multi-agent deep reinforcement learning (MADRL) approach for unmmaned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks. An UAV with computing capability can provide task offlaoding services to ground internet-of-things devices (IDs). With partial observation of the entire network state, the UAV and the IDs individually determine their MEC strategies, i.e., UAV trajectory, resource allocation, and task offloading policy. This requires joint optimization of decision-making process and coordination strategies among the UAV and the IDs. To address this difficulty, the proposed cooperative MADRL approach computes two types of action variables, namely message action and solution action, each of which is generated by dedicated actor neural networks (NNs). As a result, each agent can automatically encapsulate its coordination messages to enhance the MEC performance in the decentralized manner. The proposed actor structure is designed based on graph attention networks such that operations are possible regardless of the number of IDs. A scalable training algorithm is also proposed to train a group of NNs for arbitrary network configurations. Numerical results demonstrate the superiority of the proposed cooperative MADRL approach over conventional methods., Comment: 13 pages, 6 figures

As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably control their outputs. In this paper, we propose a visualization design, named Concept Lens, for jointly navigating the data distribution of a generative model, and concept manipulations supported by the model. Our work is focused on modern vision-based generative adversarial networks (GAN), and their learned latent spaces, wherein concept discovery has gained significant interest as a means of image manipulation. Concept Lens is designed to support users in understanding the diversity of a provided set of concepts, the relationship between concepts, and the suitability of concepts to give semantic controls for image generation. Key to our approach is the hierarchical grouping of concepts, generated images, and the associated joint exploration. We show how Concept Lens can reveal consistent semantic manipulations for editing images, while also serving as a diagnostic tool for studying the limitations and trade-offs of concept discovery methods.

Transfer function design is crucial in volume rendering, as it directly influences the visual representation and interpretation of volumetric data. However, creating effective transfer functions that align with users' visual objectives is often challenging due to the complex parameter space and the semantic gap between transfer function values and features of interest within the volume. In this work, we propose a novel approach that leverages recent advancements in language-vision models to bridge this semantic gap. By employing a fully differentiable rendering pipeline and an image-based loss function guided by language descriptions, our method generates transfer functions that yield volume-rendered images closely matching the user's intent. We demonstrate the effectiveness of our approach in creating meaningful transfer functions from simple descriptions, empowering users to intuitively express their desired visual outcomes with minimal effort. This advancement streamlines the transfer function design process and makes volume rendering more accessible to a wider range of users.

In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, the model presents greater overconfidence when responding with False. Furthermore, we analyze the relationship between the false negative problem and context and query rewriting and observe that both effectively tackle false negatives in LLMs., Comment: 12 pages, 9 figures

A novel framework for Bayesian structural model updating is presented in this study. The proposed method utilizes the surrogate unimodal encoders of a multimodal variational autoencoder (VAE). The method facilitates an approximation of the likelihood when dealing with a small number of observations. It is particularly suitable for high-dimensional correlated simultaneous observations applicable to various dynamic analysis models. The proposed approach was benchmarked using a numerical model of a single-story frame building with acceleration and dynamic strain measurements. Additionally, an example involving a Bayesian update of nonlinear model parameters for a three-degree-of-freedom lumped mass model demonstrates computational efficiency when compared to using the original VAE, while maintaining adequate accuracy for practical applications., Comment: 44 pages, 21 figures

Remarkable advances in large language models (LLMs) have enabled high-quality text summarization. However, this capability is currently accessible only through LLMs of substantial size or proprietary LLMs with usage fees. In response, smaller-scale LLMs (sLLMs) of easy accessibility and low costs have been extensively studied, yet they often suffer from missing key information and entities, i.e., low relevance, in particular, when input documents are long. We hence propose a key-element-informed instruction tuning for summarization, so-called KEITSum, which identifies key elements in documents and instructs sLLM to generate summaries capturing these key elements. Experimental results on dialogue and news datasets demonstrate that sLLM with KEITSum indeed provides high-quality summarization with higher relevance and less hallucinations, competitive to proprietary LLM., Comment: Interspeech 2024

In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task. Our methodology, PlugIR, actively utilizes the general instruction-following capability of LLMs in two ways. First, by reformulating the dialogue-form context, we eliminate the necessity of fine-tuning a retrieval model on existing visual dialogue data, thereby enabling the use of any arbitrary black-box model. Second, we construct the LLM questioner to generate non-redundant questions about the attributes of the target image, based on the information of retrieval candidate images in the current context. This approach mitigates the issues of noisiness and redundancy in the generated questions. Beyond our methodology, we propose a novel evaluation metric, Best log Rank Integral (BRI), for a comprehensive assessment of the interactive retrieval system. PlugIR demonstrates superior performance compared to both zero-shot and fine-tuned baselines in various benchmarks. Additionally, the two methodologies comprising PlugIR can be flexibly applied together or separately in various situations. Our codes are available at https://github.com/Saehyung-Lee/PlugIR., Comment: ACL 2024 Oral

The evaluation of summary quality encompasses diverse dimensions such as consistency, coherence, relevance, and fluency. However, existing summarization methods often target a specific dimension, facing challenges in generating well-balanced summaries across multiple dimensions. In this paper, we propose multi-objective reinforcement learning tailored to generate balanced summaries across all four dimensions. We introduce two multi-dimensional optimization (MDO) strategies for adaptive learning: 1) MDO_min, rewarding the current lowest dimension score, and 2) MDO_pro, optimizing multiple dimensions similar to multi-task learning, resolves conflicting gradients across dimensions through gradient projection. Unlike prior ROUGE-based rewards relying on reference summaries, we use a QA-based reward model that aligns with human preferences. Further, we discover the capability to regulate the length of summaries by adjusting the discount factor, seeking the generation of concise yet informative summaries that encapsulate crucial points. Our approach achieved substantial performance gains compared to baseline models on representative summarization datasets, particularly in the overlooked dimensions., Comment: ACL 2024

Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects intuitively. Previous SGG studies used a message-passing neural networks (MPNN) to update features, which can effectively reflect information about surrounding objects. However, these studies have failed to reflect the co-occurrence of objects during SGG generation. In addition, they only addressed the long-tail problem of the training dataset from the perspectives of sampling and learning methods. To address these two problems, we propose CooK, which reflects the Co-occurrence Knowledge between objects, and the learnable term frequency-inverse document frequency (TF-l-IDF) to solve the long-tail problem. We applied the proposed model to the SGG benchmark dataset, and the results showed a performance improvement of up to 3.8% compared with existing state-of-the-art models in SGGen subtask. The proposed method exhibits generalization ability from the results obtained, showing uniform performance improvement for all MPNN models., Comment: Accepted by ICML2024

As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as reference-free metrics, demonstrating their capability to adeptly handle novel tasks. However, these models generally rely on a single-agent approach, which, we argue, introduces an inherent limit to their performance. This is because there exist biases in LLM agent's responses, including preferences for certain text structure or content. In this work, we propose DEBATE, an NLG evaluation framework based on multi-agent scoring system augmented with a concept of Devil's Advocate. Within the framework, one agent is instructed to criticize other agents' arguments, potentially resolving the bias in LLM agent's answers. DEBATE substantially outperforms the previous state-of-the-art methods in two meta-evaluation benchmarks in NLG evaluation, SummEval and TopicalChat. We also show that the extensiveness of debates among agents and the persona of an agent can influence the performance of evaluators.

Visualizing citation relations with network structures is widely used, but the visual complexity can make it challenging for individual researchers trying to navigate them. We collected data from 18 researchers with an interface that we designed using network simplification methods and analyzed how users browsed and identified important papers. Our analysis reveals six major patterns used for identifying papers of interest, which can be categorized into three key components: Fields, Bridges, and Foundations, each viewed from two distinct perspectives: layout-oriented and connection-oriented. The connection-oriented approach was found to be more reliable for selecting relevant papers, but the layout-oriented method was adopted more often, even though it led to unexpected results and user frustration. Our findings emphasize the importance of integrating these components and the necessity to balance visual layouts with meaningful connections to enhance the effectiveness of citation networks in academic browsing systems.

When faced with accomplishing a task, human experts exhibit intentional behavior. Their unique intents shape their plans and decisions, resulting in experts demonstrating diverse behaviors to accomplish the same task. Due to the uncertainties encountered in the real world and their bounded rationality, experts sometimes adjust their intents, which in turn influences their behaviors during task execution. This paper introduces IDIL, a novel imitation learning algorithm to mimic these diverse intent-driven behaviors of experts. Iteratively, our approach estimates expert intent from heterogeneous demonstrations and then uses it to learn an intent-aware model of their behavior. Unlike contemporary approaches, IDIL is capable of addressing sequential tasks with high-dimensional state representations, while sidestepping the complexities and drawbacks associated with adversarial training (a mainstay of related techniques). Our empirical results suggest that the models generated by IDIL either match or surpass those produced by recent imitation learning benchmarks in metrics of task performance. Moreover, as it creates a generative model, IDIL demonstrates superior performance in intent inference metrics, crucial for human-agent interactions, and aptly captures a broad spectrum of expert behaviors., Comment: Extended version of an identically-titled paper accepted at AAMAS 2024

We develop a site-specific ground-motion model (GMM) for crustal earthquakes in Japan that can directly model the probability distribution of ground motion acceleration time histories based on generative adversarial networks (GANs). The proposed model can generate ground motions conditioned on moment magnitude, rupture distance, and detailed site conditions defined by the average shear-wave velocity in the top 5 m, 10 m, and 20 m ($V_{\mathrm{S}5}$, $V_{\mathrm{S}10}$, $V_{\mathrm{S}20}$) and the depth to shear-wave velocities of 1.0 km/s and 1.4 km/s ($Z_{1.0}$, $Z_{1.4}$). We construct the neural networks based on styleGAN2 and introduce a novel neural network architecture to generate ground motions considering the effect of source, path, and such detailed site conditions. 5% damped spectral acceleration of ground motions generated by the proposed GMM is consistent with empirical GMMs in terms of magnitude and distance scaling. The proposed GMM can also generate ground motions accounting for the shear-wave velocity profiles of surface soil with different magnitudes and distances, and represent characteristic that are not explained solely by $V_{\mathrm{S}30}$.

Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed identities with combined attributes from different subjects. In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects. Our main idea is to utilize segmented subjects generated by a foundation model for segmentation (Segment Anything) for both training and inference, as a form of data augmentation for training and initialization for the generation process. Moreover, we further introduce a new metric to better evaluate the performance of our method on multi-subject personalization. Experimental results show that our MuDI can produce high-quality personalized images without identity mixing, even for highly similar subjects as shown in Figure 1. Specifically, in human evaluation, MuDI obtains twice the success rate for personalizing multiple subjects without identity mixing over existing baselines and is preferred over 70% against the strongest baseline., Comment: NeurIPS 2024. Project page: https://mudi-t2i.github.io/

This study presents a novel approach to quantifying uncertainties in Bayesian model updating, which is effective in sparse or single observations. Conventional uncertainty quantification metrics such as the Euclidean and Bhattacharyya distance-based metrics are potential in scenarios with ample observations. However, their validation is limited in situations with insufficient data, particularly for nonlinear responses like post-yield behavior. Our method addresses this challenge by using the latent space of a Variational Auto-encoder (VAE), a generative model that enables nonparametric likelihood evaluation. This approach is valuable in updating model parameters based on nonlinear seismic responses of structure, wherein data scarcity is a common challenge. Our numerical experiments confirm the ability of the proposed method to accurately update parameters and quantify uncertainties using limited observations. Additionally, these numerical experiments reveal a tendency for increased information about nonlinear behavior to result in decreased uncertainty in terms of estimations. This study provides a robust tool for quantifying uncertainty in scenarios characterized by considerable uncertainty, thereby expanding the applicability of Bayesian updating methods in data-constrained environments.

The miniaturization of AI accelerators is paving the way for next-generation wearable applications within wearable technologies. We introduce Mojito, an AI-native runtime with advanced MLOps designed to facilitate the development and deployment of these applications on wearable devices. It emphasizes the necessity of dynamic orchestration of distributed resources equipped with ultra-low-power AI accelerators to overcome challenges associated with unpredictable runtime environments. Through its innovative approaches, Mojito demonstrates how future wearable technologies can evolve to be more autonomous., Comment: 7 pages, 4 figures

In recent years, deep learning has achieved innovative advancements in various fields, including the analysis of human emotions and behaviors. Initiatives such as the Affective Behavior Analysis in-the-wild (ABAW) competition have been particularly instrumental in driving research in this area by providing diverse and challenging datasets that enable precise evaluation of complex emotional states. This study leverages the Vision Transformer (ViT) and Transformer models to focus on the estimation of Valence-Arousal (VA), which signifies the positivity and intensity of emotions, recognition of various facial expressions, and detection of Action Units (AU) representing fundamental muscle movements. This approach transcends traditional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) based methods, proposing a new Transformer-based framework that maximizes the understanding of temporal and spatial features. The core contributions of this research include the introduction of a learning technique through random frame masking and the application of Focal loss adapted for imbalanced data, enhancing the accuracy and applicability of emotion and behavior analysis in real-world settings. This approach is expected to contribute to the advancement of emotional computing and deep learning methodologies.

In robot-assisted minimally invasive surgery (RAMIS), optimal placement of the surgical robot base is crucial for successful surgery. Improper placement can hinder performance because of manipulator limitations and inaccessible workspaces. Conventional base placement relies on the experience of trained medical staff. This study proposes a novel method for determining the optimal base pose based on the surgeon's working pattern. The proposed method analyzes recorded end-effector poses using a machine learning-based clustering technique to identify key positions and orientations preferred by the surgeon. We introduce two scoring metrics to address the joint limit and singularity issues: joint margin and manipulability scores. We then train a multi-layer perceptron regressor to predict the optimal base pose based on these scores. Evaluation in a simulated environment using the da Vinci Research Kit shows unique base pose score maps for four volunteers, highlighting the individuality of the working patterns. Results comparing with 20,000 randomly selected base poses suggest that the score obtained using the proposed method is 28.2% higher than that obtained by random base placement. These results emphasize the need for operator-specific optimization during base placement in RAMIS., Comment: 8 pages, 7 figures, 2 tables

Monocular depth estimation (MDE) is essential for numerous applications yet is impeded by the substantial computational demands of accurate deep learning models. To mitigate this, we introduce a novel Teacher-Independent Explainable Knowledge Distillation (TIE-KD) framework that streamlines the knowledge transfer from complex teacher models to compact student networks, eliminating the need for architectural similarity. The cornerstone of TIE-KD is the Depth Probability Map (DPM), an explainable feature map that interprets the teacher's output, enabling feature-based knowledge distillation solely from the teacher's response. This approach allows for efficient student learning, leveraging the strengths of feature-based distillation. Extensive evaluation of the KITTI dataset indicates that TIE-KD not only outperforms conventional response-based KD methods but also demonstrates consistent efficacy across diverse teacher and student architectures. The robustness and adaptability of TIE-KD underscore its potential for applications requiring efficient and interpretable models, affirming its practicality for real-world deployment., Comment: 13 pages, 8 figures, under review for a journal

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task Inference. For this purpose, we introduce the MTI Bench(Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks. Each task in the MTI Bench involves 2 to 3 sub-tasks. As expected, we first demonstrate that Multi-Task Inference reduces the total inference time by 1.46 times in average since it does not require multiple inference calls. Interestingly, contrary to the expectation that LLMs would perform better when tasks are divided, we find that state-of-the-art LLMs, such as Llama-2-Chat-70B and GPT-4, show up to 7.3% and 12.4% improved performance with Multi-Task Inference compared to Single-Task Inference on the MTI Bench. We release the MTI Bench dataset and our code at this link https://github.com/guijinSON/MTI-Bench., Comment: acl 2024 (main)

Large-Language Models (LLMs) have shifted the paradigm of natural language data processing. However, their black-boxed and probabilistic characteristics can lead to potential risks in the quality of outputs in diverse LLM applications. Recent studies have tested Quality Attributes (QAs), such as robustness or fairness, of LLMs by generating adversarial input texts. However, existing studies have limited their coverage of QAs and tasks in LLMs and are difficult to extend. Additionally, these studies have only used one evaluation metric, Attack Success Rate (ASR), to assess the effectiveness of their approaches. We propose a MEtamorphic Testing for Analyzing LLMs (METAL) framework to address these issues by applying Metamorphic Testing (MT) techniques. This approach facilitates the systematic testing of LLM qualities by defining Metamorphic Relations (MRs), which serve as modularized evaluation metrics. The METAL framework can automatically generate hundreds of MRs from templates that cover various QAs and tasks. In addition, we introduced novel metrics that integrate the ASR method into the semantic qualities of text to assess the effectiveness of MRs accurately. Through the experiments conducted with three prominent LLMs, we have confirmed that the METAL framework effectively evaluates essential QAs on primary LLM tasks and reveals the quality risks in LLMs. Moreover, the newly proposed metrics can guide the optimal MRs for testing each task and suggest the most effective method for generating MRs., Comment: Accepted to International Conference on Software Testing, Verification and Validation (ICST) 2024 / Key words: Large-language models, Metamorphic testing, Quality evaluation, Text perturbations

This study performs BERT-based analysis, which is a representative contextualized language model, on corporate disclosure data to predict impending bankruptcies. Prior literature on bankruptcy prediction mainly focuses on developing more sophisticated prediction methodologies with financial variables. However, in our study, we focus on improving the quality of input dataset. Specifically, we employ BERT model to perform sentiment analysis on MD&A disclosures. We show that BERT outperforms dictionary-based predictions and Word2Vec-based predictions in terms of adjusted R-square in logistic regression, k-nearest neighbor (kNN-5), and linear kernel support vector machine (SVM). Further, instead of pre-training the BERT model from scratch, we apply self-learning with confidence-based filtering to corporate disclosure data (10-K). We achieve the accuracy rate of 91.56% and demonstrate that the domain adaptation procedure brings a significant improvement in prediction accuracy.

Kyle (1985) proposes two types of rumors: informed rumors which are based on some private information and uninformed rumors which are not based on any information (i.e. bluffing). Also, prior studies find that when people have credible source of information, they are likely to use a more confident textual tone in their spreading of rumors. Motivated by these theoretical findings, we propose a double-channel structure to determine the ex-ante veracity of rumors on social media. Our ultimate goal is to classify each rumor into true, false, or unverifiable category. We first assign each text into either certain (informed rumor) or uncertain (uninformed rumor) category. Then, we apply lie detection algorithm to informed rumors and thread-reply agreement detection algorithm to uninformed rumors. Using the dataset of SemEval 2019 Task 7, which requires ex-ante threefold classification (true, false, or unverifiable) of social media rumors, our model yields a macro-F1 score of 0.4027, outperforming all the baseline models and the second-place winner (Gorrell et al., 2019). Furthermore, we empirically validate that the double-channel structure outperforms single-channel structures which use either lie detection or agreement detection algorithm to all posts.

Few studies have investigated the diagnostic utilities of biomarkers for predicting bacteremia among septic patients admitted to intensive care units (ICU). Therefore, this study evaluated the prediction power of laboratory biomarkers to utilize those markers with high performance to optimize the predictive model for bacteremia. This retrospective cross-sectional study was conducted at the ICU department of Gyeongsang National University Changwon Hospital in 2019. Adult patients qualifying SEPSIS-3 (increase in sequential organ failure score greater than or equal to 2) criteria with at least two sets of blood culture were selected. Collected data was initially analyzed independently to identify the significant predictors, which was then used to build the multivariable logistic regression (MLR) model. A total of 218 patients with 48 cases of true bacteremia were analyzed in this research. Both CRP and PCT showed a substantial area under the curve (AUC) value for discriminating bacteremia among septic patients (0.757 and 0.845, respectively). To further enhance the predictive accuracy, we combined PCT, bilirubin, neutrophil lymphocyte ratio (NLR), platelets, lactic acid, erythrocyte sedimentation rate (ESR), and Glasgow Coma Scale (GCS) score to build the predictive model with an AUC of 0.907 (95% CI, 0.843 to 0.956). In addition, a high association between bacteremia and mortality rate was discovered through the survival analysis (0.004). While PCT is certainly a useful index for distinguishing patients with and without bacteremia by itself, our MLR model indicates that the accuracy of bacteremia prediction substantially improves by the combined use of PCT, bilirubin, NLR, platelets, lactic acid, ESR, and GCS score., Comment: This article is not the right fit to be published as preprint in arXiv

Controlled text generation is very important for the practical use of language models because it ensures that the produced text includes only the desired attributes from a specific domain or dataset. Existing methods, however, are inapplicable to black-box models or suffer a significant trade-off between controlling the generated text and maintaining its fluency. This paper introduces the Score-based Progressive Editor (ScoPE), a novel approach designed to overcome these issues. ScoPE modifies the context at the token level during the generation process of a backbone language model. This modification guides the subsequent text to naturally include the target attributes. To facilitate this process, ScoPE employs a training objective that maximizes a target score, thoroughly considering both the ability to guide the text and its fluency. Experimental results on diverse controlled generation tasks demonstrate that ScoPE can effectively regulate the attributes of the generated text while fully utilizing the capability of the backbone large language models. Our codes are available at \url{https://github.com/ysw1021/ScoPE}., Comment: To appear in ACL 2024 Main

This paper presents ExPECA, an edge computing and wireless communication research testbed designed to tackle two pressing challenges: comprehensive end-to-end experimentation and high levels of experimental reproducibility. Leveraging OpenStack-based Chameleon Infrastructure (CHI) framework for its proven flexibility and ease of operation, ExPECA is located in a unique, isolated underground facility, providing a highly controlled setting for wireless experiments. The testbed is engineered to facilitate integrated studies of both communication and computation, offering a diverse array of Software-Defined Radios (SDR) and Commercial Off-The-Shelf (COTS) wireless and wired links, as well as containerized computational environments. We exemplify the experimental possibilities of the testbed using OpenRTiST, a latency-sensitive, bandwidth-intensive application, and analyze its performance. Lastly, we highlight an array of research domains and experimental setups that stand to gain from ExPECA's features, including closed-loop applications and time-sensitive networking.

Along with generative AI, interest in scene graph generation (SGG), which comprehensively captures the relationships and interactions between objects in an image and creates a structured graph-based representation, has significantly increased in recent years. However, relying on object-centric and dichotomous relationships, existing SGG methods have a limited ability to accurately predict detailed relationships. To solve these problems, a new approach to the modeling multiobject relationships, called edge dual scene graph generation (EdgeSGG), is proposed herein. EdgeSGG is based on a edge dual scene graph and Dual Message Passing Neural Network (DualMPNN), which can capture rich contextual interactions between unconstrained objects. To facilitate the learning of edge dual scene graphs with a symmetric graph structure, the proposed DualMPNN learns both object- and relation-centric features for more accurately predicting relation-aware contexts and allows fine-grained relational updates between objects. A comparative experiment with state-of-the-art (SoTA) methods was conducted using two public datasets for SGG operations and six metrics for three subtasks. Compared with SoTA approaches, the proposed model exhibited substantial performance improvements across all SGG subtasks. Furthermore, experiment on long-tail distributions revealed that incorporating the relationships between objects effectively mitigates existing long-tail problems.