Search

Self-supervised monocular depth estimation (SSMDE) aims to predict the dense depth map of a monocular image, by learning depth from RGB image sequences, eliminating the need for ground-truth depth labels. Although this approach simplifies data acquisition compared to supervised methods, it struggles with reflective surfaces, as they violate the assumptions of Lambertian reflectance, leading to inaccurate training on such surfaces. To tackle this problem, we propose a novel training strategy for an SSMDE by leveraging triplet mining to pinpoint reflective regions at the pixel level, guided by the camera geometry between different viewpoints. The proposed reflection-aware triplet mining loss specifically penalizes the inappropriate photometric error minimization on the localized reflective regions while preserving depth accuracy in non-reflective areas. We also incorporate a reflection-aware knowledge distillation method that enables a student model to selectively learn the pixel-level knowledge from reflective and non-reflective regions. This results in robust depth estimation across areas. Evaluation results on multiple datasets demonstrate that our method effectively enhances depth quality on reflective surfaces and outperforms state-of-the-art SSMDE baselines., Comment: Accepted at ICLR 2025

Recent studies have combined Large Language Models (LLMs) with Knowledge Graphs (KGs) to enhance reasoning, improving inference accuracy without additional training while mitigating hallucination. However, existing frameworks are often rigid, struggling to adapt to KG or task changes. They also rely heavily on powerful LLMs for reliable (i.e., trustworthy) reasoning. To address this, We introduce R2-KG, a plug-and-play, dual-agent framework that separates reasoning into two roles: an Operator (a low-capacity LLM) that gathers evidence and a Supervisor (a high-capacity LLM) that makes final judgments. This design is cost-efficient for LLM inference while still maintaining strong reasoning accuracy. Additionally, R2-KG employs an Abstention mechanism, generating answers only when sufficient evidence is collected from KG, which significantly enhances reliability. Experiments across multiple KG-based reasoning tasks show that R2-KG consistently outperforms baselines in both accuracy and reliability, regardless of the inherent capability of LLMs used as the Operator. Further experiments reveal that the single-agent version of R2-KG, equipped with a strict self-consistency strategy, achieves significantly higher-than-baseline reliability while reducing inference cost. However, it also leads to a higher abstention rate in complex KGs. Our findings establish R2-KG as a flexible and cost-effective solution for KG-based reasoning. It reduces reliance on high-capacity LLMs while ensuring trustworthy inference.

Ultrafast light-matter interactions inspire potential functionalities in picosecond optoelectronic applications. However, achieving directional carrier dynamics in metals remains challenging due to strong carrier scattering within a multiband environment, typically expected to isotropic carrier relaxation. In this study, we demonstrate epitaxial RuO2/TiO2 (110) heterostructures grown by hybrid molecular beam epitaxy to engineer polarization-selectivity of ultrafast light-matter interactions via anisotropic strain engineering. Combining spectroscopic ellipsometry, X-ray absorption spectroscopy, and optical pump-probe spectroscopy, we revealed the strong anisotropic transient optoelectronic response of strain-engineered RuO2/TiO2 (110) heterostructures along both in-plane [001] and [1-10] crystallographic directions. Theoretical analysis identifies strain-induced modifications in band nesting as the underlying mechanism for enhanced anisotropic carrier relaxation. These findings establish epitaxial strain engineering as a powerful tool for tuning anisotropic optoelectronic responses in metallic systems, paving the way for next-generation polarization-sensitive ultrafast optoelectronic devices., Comment: 18 pages

We address the convergence problem in learning the Optimal Transport (OT) map, where the OT Map refers to a map from one distribution to another while minimizing the transport cost. Semi-dual Neural OT, a widely used approach for learning OT Maps with neural networks, often generates fake solutions that fail to transfer one distribution to another accurately. We identify a sufficient condition under which the max-min solution of Semi-dual Neural OT recovers the true OT Map. Moreover, to address cases when this sufficient condition is not satisfied, we propose a novel method, OTP, which learns both the OT Map and the Optimal Transport Plan, representing the optimal coupling between two distributions. Under sharp assumptions on the distributions, we prove that our model eliminates the fake solution issue and correctly solves the OT problem. Our experiments show that the OTP model recovers the optimal transport map where existing methods fail and outperforms current OT-based models in image-to-image translation tasks. Notably, the OTP model can learn stochastic transport maps when deterministic OT Maps do not exist, such as one-to-many tasks like colorization., Comment: 18 pages, 10 figures

We report limits on WIMP dark matter derived from three years of data collected by the COSINE-100 experiment with NaI(Tl) crystals, achieving an improved energy threshold of 0.7 keV. This lowered threshold enhances sensitivity in the sub-GeV mass range, extending the reach for direct detection of low-mass dark matter. Although no excess of WIMP-like events was observed, the increased sensitivity enabled a model-independent comparison between the expected WIMP signal rate-based on mass limits from our data-and DAMA's reported modulation amplitude. Our findings strongly disfavor the DAMA signal as originating from WIMP interactions, fully excluding DAMA/LIBRA 3$\sigma$ allowed regions and providing enhanced WIMP mass limits by an order of magnitude in the spin-independent model compared to previous results. In the spin-dependent model, cross-section upper limits were obtained in the mass range [0.1-5.0] GeV/c$^2$, with additional sensitivity to sub-GeV WIMPs through the inclusion of the Migdal effect. These results represent substantial progress in low-mass dark matter exploration and reinforce constraints on the longstanding DAMA claim.

The anomalous Hall effect (AHE), a hallmark of time-reversal symmetry breaking, has been reported in rutile RuO2, a debated metallic altermagnetic candidate. Previously, AHE in RuO2 was observed only in strain-relaxed thick films under extremely high magnetic fields (~50 T). Yet, in ultrathin strained films with distinctive anisotropic electronic structures, there are no reports, likely due to disorder and defects suppressing metallicity thus hindering its detection. Here, we demonstrate that ultrathin, fully-strained 2 nm TiO2/t nm RuO2/TiO2 (110) heterostructures, grown by hybrid molecular beam epitaxy, retain metallicity and exhibit a sizeable AHE at a significantly lower magnetic field (< 9 T). Density functional theory calculations reveal that epitaxial strain stabilizes a non-compensated magnetic ground state and reconfigures magnetic ordering in RuO2 (110) thin films. These findings establish ultrathin RuO2 as a platform for strain-engineered magnetism and underscore the transformative potential of epitaxial design in advancing spintronic technologies., Comment: 23 pages

As chatbots become increasingly integrated into everyday tasks, designing systems that accommodate diverse user populations is crucial for fostering trust, engagement, and inclusivity. This study investigates the ability of contemporary Large Language Models (LLMs) to generate African American Vernacular English (AAVE) and evaluates the impact of AAVE usage on user experiences in chatbot applications. We analyze the performance of three LLM families (Llama, GPT, and Claude) in producing AAVE-like utterances at varying dialect intensities and assess user preferences across multiple domains, including healthcare and education. Despite LLMs' proficiency in generating AAVE-like language, findings indicate that AAVE-speaking users prefer Standard American English (SAE) chatbots, with higher levels of AAVE correlating with lower ratings for a variety of characteristics, including chatbot trustworthiness and role appropriateness. These results highlight the complexities of creating inclusive AI systems and underscore the need for further exploration of diversity to enhance human-computer interactions.

Scientific figure captioning is a complex task that requires generating contextually appropriate descriptions of visual content. However, existing methods often fall short by utilizing incomplete information, treating the task solely as either an image-to-text or text summarization problem. This limitation hinders the generation of high-quality captions that fully capture the necessary details. Moreover, existing data sourced from arXiv papers contain low-quality captions, posing significant challenges for training large language models (LLMs). In this paper, we introduce a framework called Multi-LLM Collaborative Figure Caption Generation (MLBCAP) to address these challenges by leveraging specialized LLMs for distinct sub-tasks. Our approach unfolds in three key modules: (Quality Assessment) We utilize multimodal LLMs to assess the quality of training data, enabling the filtration of low-quality captions. (Diverse Caption Generation) We then employ a strategy of fine-tuning/prompting multiple LLMs on the captioning task to generate candidate captions. (Judgment) Lastly, we prompt a prominent LLM to select the highest quality caption from the candidates, followed by refining any remaining inaccuracies. Human evaluations demonstrate that informative captions produced by our approach rank better than human-written captions, highlighting its effectiveness. Our code is available at https://github.com/teamreboott/MLBCAP, Comment: Accepted to AAAI 2025 AI4Research Workshop

Although being widely adopted for evaluating generated audio signals, the Fr\'echet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumptions, sensitivity to sample size, and high computational complexity. As an alternative, we introduce the Kernel Audio Distance (KAD), a novel, distribution-free, unbiased, and computationally efficient metric based on Maximum Mean Discrepancy (MMD). Through analysis and empirical validation, we demonstrate KAD's advantages: (1) faster convergence with smaller sample sizes, enabling reliable evaluation with limited data; (2) lower computational cost, with scalable GPU acceleration; and (3) stronger alignment with human perceptual judgments. By leveraging advanced embeddings and characteristic kernels, KAD captures nuanced differences between real and generated audio. Open-sourced in the kadtk toolkit, KAD provides an efficient, reliable, and perceptually aligned benchmark for evaluating generative audio models.

Interpretability for machine learning models is becoming more and more important as machine learning models become more complex. The functional ANOVA model, which decomposes a high-dimensional function into a sum of lower dimensional functions so called components, is one of the most popular tools for interpretable AI, and recently, various neural network models have been developed for estimating each component in the functional ANOVA model. However, such neural networks are highly unstable when estimating components since the components themselves are not uniquely defined. That is, there are multiple functional ANOVA decompositions for a given function. In this paper, we propose a novel interpretable model which guarantees a unique functional ANOVA decomposition and thus is able to estimate each component stably. We call our proposed model ANOVA-NODE since it is a modification of Neural Oblivious Decision Ensembles (NODE) for the functional ANOVA model. Theoretically, we prove that ANOVA-NODE can approximate a smooth function well. Additionally, we experimentally show that ANOVA-NODE provides much more stable estimation of each component and thus much more stable interpretation when training data and initial values of the model parameters vary than existing neural network models do., Comment: 45 pages

Ultrafast optical excitation of quantum materials has opened new frontiers for transiently inducing novel phases of matter, including magnetism, charge density waves, ferroelectricity, and superconductivity beyond the constraints of equilibrium thermodynamics. Triggering a transient topological order in a trivial semiconductor represents a key milestone, as it could provide an on-demand route to topological functionality for device applications. However, achieving a topologically nontrivial phase from a large-gap (~ 1 eV) semiconductor remains a major challenge, as substantial energy modification is required to invert the band gap. Here, we report the discovery of a thermally inaccessible, transient topological crystalline order in a sizable-gap (~ 0.8 eV) layered semiconductor, SnSe, through femtosecond above-gap excitation. Time- and angle-resolved photoemission spectroscopy reveals a Dirac-like linear dispersion forming within the band gap on a subpicosecond timescale. This transient state shows hallmark features of a reflection-invariant topological crystalline insulator, including a high Fermi velocity (2.5x10^5 m/s), multiple Dirac points located away from high-symmetry momenta, and independence from probe photon energy, persisting for several picoseconds even at room temperature. Our findings establish a nonequilibrium pathway to ultrafast topological order in a semiconductor, opening new avenues for optically driven spintronic and quantum information technologies., Comment: 24 pages, 4 figures

In traditional voter models, opinion dynamics are driven by interactions between individuals, where an individual adopts the opinion of a randomly chosen neighbor. However, these models often fail to capture the emergence of entirely new opinions, which can arise spontaneously in real-world scenarios. Our study introduces a novel element to the classic voter model: the concept of innovation, where individuals have a certain probability of generating new opinions independently of their neighbors' states. This innovation process allows for a more realistic representation of social dynamics, where new opinions can emerge and old ones may fade over time. Through analytical and numerical analysis, we find that the balance between innovation and extinction shapes the number of opinions in the steady state. Specifically, for low innovation rates, the system tends toward near-consensus, while higher innovation rates lead to greater opinion diversity. We also show that network structure influences opinion dynamics, with greater degree heterogeneity reducing the number of opinions in the system., Comment: 9 pages, 7 figures

In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduced training time. DeepDeblurRF leverages deep neural network (DNN)-based deblurring modules to enjoy their deblurring performance and computational efficiency. To effectively combine DNN-based deblurring and radiance field construction, we propose a novel radiance field (RF)-guided deblurring and an iterative framework that performs RF-guided deblurring and radiance field construction in an alternating manner. Moreover, DeepDeblurRF is compatible with various scene representations, such as voxel grids and 3D Gaussians, expanding its applicability. We also present BlurRF-Synth, the first large-scale synthetic dataset for training radiance field deblurring frameworks. We conduct extensive experiments on both camera motion blur and defocus blur, demonstrating that DeepDeblurRF achieves state-of-the-art novel-view synthesis quality with significantly reduced training time.

Lab tests are fundamental for diagnosing diseases and monitoring patient conditions. However, frequent testing can be burdensome for patients, and test results may not always be immediately available. To address these challenges, we propose LabTOP, a unified model that predicts lab test outcomes by leveraging a language modeling approach on EHR data. Unlike conventional methods that estimate only a subset of lab tests or classify discrete value ranges, LabTOP performs continuous numerical predictions for a diverse range of lab items. We evaluate LabTOP on three publicly available EHR datasets and demonstrate that it outperforms existing methods, including traditional machine learning models and state-of-the-art large language models. We also conduct extensive ablation studies to confirm the effectiveness of our design choices. We believe that LabTOP will serve as an accurate and generalizable framework for lab test outcome prediction, with potential applications in clinical decision support and early detection of critical conditions., Comment: 11 pages for main text, 4 pages for appendix

Fine-tuning text-to-image diffusion models to maximize rewards has proven effective for enhancing model performance. However, reward fine-tuning methods often suffer from slow convergence due to online sample generation. Therefore, obtaining diverse samples with strong reward signals is crucial for improving sample efficiency and overall performance. In this work, we introduce DiffExp, a simple yet effective exploration strategy for reward fine-tuning of text-to-image models. Our approach employs two key strategies: (a) dynamically adjusting the scale of classifier-free guidance to enhance sample diversity, and (b) randomly weighting phrases of the text prompt to exploit high-quality reward signals. We demonstrate that these strategies significantly enhance exploration during online sample generation, improving the sample efficiency of recent reward fine-tuning methods, such as DDPO and AlignProp., Comment: AAAI 2025

We present TalkPlay, a multimodal music recommendation system that reformulates the recommendation task as large language model token generation. TalkPlay represents music through an expanded token vocabulary that encodes multiple modalities - audio, lyrics, metadata, semantic tags, and playlist co-occurrence. Using these rich representations, the model learns to generate recommendations through next-token prediction on music recommendation conversations, that requires learning the associations natural language query and response, as well as music items. In other words, the formulation transforms music recommendation into a natural language understanding task, where the model's ability to predict conversation tokens directly optimizes query-item relevance. Our approach eliminates traditional recommendation-dialogue pipeline complexity, enabling end-to-end learning of query-aware music recommendations. In the experiment, TalkPlay is successfully trained and outperforms baseline methods in various aspects, demonstrating strong context understanding as a conversational music recommender.

Large Language Models (LLMs) enhance their problem-solving capability by leveraging both parametric and external knowledge. Beyond leveraging external knowledge to improve response accuracy, they require key capabilities for reliable knowledge-handling: resolving conflicts between knowledge sources, avoiding distraction from uninformative external knowledge, and abstaining when sufficient knowledge is unavailable. Prior studies have examined these scenarios in isolation or with limited scope. To systematically evaluate these capabilities, we introduce a comprehensive framework for analyzing knowledge-handling based on two key dimensions: the presence of parametric knowledge and the informativeness of external knowledge. Through analysis, we identify biases in knowledge utilization and examine how the ability to handle one scenario impacts performance in others. Furthermore, we demonstrate that training on data constructed based on the knowledge-handling scenarios improves LLMs' reliability in integrating and utilizing knowledge., Comment: under-review

Using $(2712\pm14)\times10^6$ $\psi(3686)$ events collected with the BESIII detector, we perform the first amplitude analysis of the radiative decay $\psi(3686)\to \gamma K_S^0 K_S^0$ within the mass region $M_{K_S^0 K_S^0 }<2.8$ GeV/$c^2$. Employing a one-channel K-matrix approach for the description of the dynamics of the $K^0_S K^0_S$ system, the data sample is well described with four poles for the $f_0$-wave and three poles for the $f_2$-wave. The determined pole positions are consistent with those of well-established resonance states. The observed $f_0$ and $f_{2}$ states are found to be qualitatively consistent with those produced in radiative $J/\psi$ decays, indicating the similarity between the two charmonium states in their radiative decays., Comment: 20 pages, 4 figures, submitted to JHEP

We report a measurement of the inelasticity distribution in the scattering of neutrinos of energy $80-560$ GeV off nucleons, which is sensitive to the inclusive differential cross section. This analysis is based on a sample of atmospheric muon neutrinos detected in the IceCube sub-array DeepCore during 2012-2021, and is the first such measurement in this energy range. Our measurement extends to energies where accelerator data is not available, hence we compare our results to predictions from perturbative QCD calculations, finding good agreement., Comment: 17 pages, 19 figures

Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset. However, DPO has the limitation that the KL penalty, which prevents excessive deviation from the reference model, is static throughout the training process. Several methods try to turn this static KL penalty into a dynamic one, but no approach can adaptively assign different KL penalties for each preference pair. In this paper, we propose $\varepsilon$-Direct Preference Optimization ($\varepsilon$-DPO), which allows adaptive control of the KL penalty strength $\beta$ for each preference pair. Specifically, $\varepsilon$-DPO adaptively controls $\beta$ for each preference pair based on the monotonicity of logits as a preference model under the perturbation of $\beta$ during training by simply reusing the logit of the current policy and the reference policy. Experimental results show that $\varepsilon$-DPO outperforms existing direct alignment algorithms and KL penalty relaxation methods on general chatbot benchmarks, highlighting the significance of adaptive KL penalty relaxation at the instance-level in DPO., Comment: Preprint; Under review

A Bug Inducing Commit (BIC) is a code change that introduces a bug into the codebase. Although the abnormal or unexpected behavior caused by the bug may not manifest immediately, it will eventually lead to program failures further down the line. When such a program failure is observed, identifying the relevant BIC can aid in the bug resolution process, because knowing the original intent and context behind the code change, as well as having a link to the author of that change, can facilitate bug triaging and debugging. However, existing BIC identification techniques have limitations. Bisection can be computationally expensive because it requires executing failing tests against previous versions of the codebase. Other techniques rely on the availability of specific post hoc artifacts, such as bug reports or bug fixes. In this paper, we propose a technique called Fonte that aims to identify the BIC with a core concept that a commit is more likely to be a BIC if it has more recently modified code elements that are highly suspicious of containing the bug. To realise this idea, Fonte leverages two fundamental relationships in software: the failure-to-code relationship, which can be quantified through fault localisation techniques, and the code-to-commit relationship, which can be obtained from version control systems. Our empirical evaluation using 206 real-world BICs from open-source Java projects shows that Fonte significantly outperforms state-of-the-art BIC identification techniques, achieving up to 45.8% higher MRR. We also report that the ranking scores produced by Fonte can be used to perform weighted bisection. Finally, we apply Fonte to a large-scale industry project with over 10M lines of code, and show that it can rank the actual BIC within the top five commits for 87% of the studied real batch-testing failures, and save the BIC inspection cost by 32% on average., Comment: 14 pages, 10 figures. Extended version of Fonte (ICSE'23, arXiv:2212.06376)

This paper presents a novel learning-based approach to dynamic robot-to-human handover, addressing the challenges of delivering objects to a moving receiver. We hypothesize that dynamic handover, where the robot adjusts to the receiver's movements, results in more efficient and comfortable interaction compared to static handover, where the receiver is assumed to be stationary. To validate this, we developed a nonparametric method for generating continuous handover motion, conditioned on the receiver's movements, and trained the model using a dataset of 1,000 human-to-human handover demonstrations. We integrated preference learning for improved handover effectiveness and applied impedance control to ensure user safety and adaptiveness. The approach was evaluated in both simulation and real-world settings, with user studies demonstrating that dynamic handover significantly reduces handover time and improves user comfort compared to static methods. Videos and demonstrations of our approach are available at https://zerotohero7886.github.io/dyn-r2h-handover ., Comment: Accepted to ICRA 2025. For associated videos, see https://zerotohero7886.github.io/dyn-r2h-handover

We present a novel 3D reconstruction pipeline for 360$^\circ$ cameras for 3D mapping and rendering of indoor environments. Traditional Structure-from-Motion (SfM) methods may not work well in large-scale indoor scenes due to the prevalence of textureless and repetitive regions. To overcome these challenges, our approach (IM360) leverages the wide field of view of omnidirectional images and integrates the spherical camera model into every core component of the SfM pipeline. In order to develop a comprehensive 3D reconstruction solution, we integrate a neural implicit surface reconstruction technique to generate high-quality surfaces from sparse input data. Additionally, we utilize a mesh-based neural rendering approach to refine texture maps and accurately capture view-dependent properties by combining diffuse and specular components. We evaluate our pipeline on large-scale indoor scenes from the Matterport3D and Stanford2D3D datasets. In practice, IM360 demonstrate superior performance in terms of textured mesh reconstruction over SOTA. We observe accuracy improvements in terms of camera localization and registration as well as rendering high frequency details.

Cyanobacterial blooms (CBs) pose significant global challenges due to their harmful toxins and socio-economic impacts, with nutrient availability playing a key role in their growth, as described by ecological stoichiometry (ES). However, real-world ecosystems exhibit spatial heterogeneity, limiting the applicability of simpler, spatially uniform models. To address this, we develop a spatially explicit partial differential equation model based on ES to study cyanobacteria in the epilimnion of freshwater systems. We establish the well-posedness of the model and perform a stability analysis, showing that it admits two linearly stable steady states, leading to either extinction or saturation. We use the finite elements method to numerically solve our system on a real lake domain derived from Geographic Information System (GIS) data and realistic wind conditions extrapolated from ERA5-Land. Our numerical results highlight the importance of lake shape and size in CB monitoring, while global sensitivity analysis using Sobol Indices identifies light attenuation and intensity as primary drivers of bloom variation, with water movement influencing early bloom stages and nutrient input becoming critical over time. This model supports continuous water-quality monitoring, informing agricultural, recreational, economic, and public health strategies for mitigating CBs.

Access to digital information is a driver of economic development. But although 85% of sub-Saharan Africa's population is covered by mobile broadband signal, only 37% use the internet, and those who do seldom use the web. We investigate whether AI can bridge this gap by analyzing how 469 teachers use an AI chatbot in Sierra Leone. The chatbot, accessible via a common messaging app, is compared against traditional web search. Teachers use AI more frequently than web search for teaching assistance. Data cost is the most frequently cited reason for low internet usage across Africa. The average web search result consumes 3,107 times more data than an AI response, making AI 87% less expensive than web search. Additionally, only 2% of results for corresponding web searches contain content from Sierra Leone. In blinded evaluations, an independent sample of teachers rate AI responses as more relevant, helpful, and correct than web search results. These findings suggest that AI-driven solutions can cost-effectively bridge information gaps in low-connectivity regions.

We find information geometry of tempered stable processes. Starting with the derivation of $\alpha$-divergence between two tempered stable processes, Fisher information matrices of tempered stable processes and $\alpha$-connections of their statistical manifolds are obtained. Additionally, we also provide statistical applications for the information geometry of tempered stable processes. Various tempered stable processes such as generalized tempered stable processes, classical tempered stable processes, and rapidly decreasing tempered stable processes are given as examples., Comment: 21 pages

Modelling epidemics using contact networks provides a significant improvement over classical compartmental models by explicitly incorporating the network of contacts. However, while network-based models describe disease spread on a given contact structure, their potential for inferring the underlying network from epidemic data remains largely unexplored. In this work, we consider the edge-based compartmental model (EBCM), a compact and analytically tractable framework, and we integrate it within dynamical survival analysis (DSA) to infer key network properties along with parameters of the epidemic itself. Despite correlations between structural and epidemic parameters, our framework demonstrates robustness in accurately inferring contact network properties from synthetic epidemic simulations. Additionally, we apply the framework to real-world outbreaks, namely the 2001 UK foot-and-mouth disease outbreak and the COVID-19 epidemic in Seoul, to estimate both disease parameters and network characteristics. Our results show that our framework achieves good fits to real-world epidemic data and reliable short-term forecasts. These findings highlight the potential of network-based inference approaches to uncover hidden contact structures, providing insights that can inform the design of targeted interventions and public health strategies.

Existing LLM reasoning methods have shown impressive capabilities across various tasks, such as solving math and coding problems. However, applying these methods to scenarios without ground-truth answers or rule-based verification methods - such as tracking the mental states of an agent - remains challenging. Inspired by the sequential Monte Carlo algorithm, we introduce thought-tracing, an inference-time reasoning algorithm designed to trace the mental states of specific agents by generating hypotheses and weighting them based on observations without relying on ground-truth solutions to questions in datasets. Our algorithm is modeled after the Bayesian theory-of-mind framework, using LLMs to approximate probabilistic inference over agents' evolving mental states based on their perceptions and actions. We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements compared to baseline LLMs. Our experiments also reveal interesting behaviors of the recent reasoning models - e.g., o1 and R1 - on theory-of-mind, highlighting the difference of social reasoning compared to other domains.

Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyze this dependence using multiple machine learning methods and a dataset of > 200,000 nonlinear simulations of ion-temperature-gradient turbulence in diverse non-axisymmetric geometries. The dataset is generated using a large collection of both optimized and randomly generated stellarator equilibria. At fixed gradients, the turbulent heat flux varies between geometries by several orders of magnitude. Trends are apparent among the configurations with particularly high or low heat flux. Regression and classification techniques from machine learning are then applied to extract patterns in the dataset. Due to a symmetry of the gyrokinetic equation, the heat flux and regressions thereof should be invariant to translations of the raw features in the parallel coordinate, similar to translation invariance in computer vision applications. Multiple regression models including convolutional neural networks (CNNs) and decision trees can achieve reasonable predictive power for the heat flux in held-out test configurations, with highest accuracy for the CNNs. Using Spearman correlation, sequential feature selection, and Shapley values to measure feature importance, it is consistently found that the most important geometric lever on the heat flux is the flux surface compression in regions of bad curvature. The second most important feature relates to the magnitude of geodesic curvature. These two features align remarkably with surrogates that have been proposed based on theory, while the methods here allow a natural extension to more features for increased accuracy. The dataset, released with this publication, may also be used to test other proposed surrogates, and we find many previously published proxies do correlate well with both the heat flux and stability boundary.

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor dysfunction and abnormal neural oscillations. These symptoms can be modulated through electrical stimulation. Traditional neural activity analysis in PD has typically relied on statistical methods, which often introduce bias owing to the need for expert-driven feature extraction. To address this limitation, we explore an explainable artificial intelligence (XAI) approach to analyze neural activity in Parkinsonian rats receiving electrical stimulation. Electrocorticogram (ECoG) signals were collected before and after electrical stimulation using graphene-based electrodes that enable less-invasive monitoring and stimulation in PD. EEGNet, a convolutional neural network, classified these ECoG signals into pre- and post-stimulation states. We applied layer-wise relevance propagation, an XAI technique, to identify key neural inputs contributing to the model's decisions, incorporating the spatial electrode information matched to the cortex map. The XAI analysis highlighted area-specific importance in beta and gamma frequency bands, which could not be detected through mean comparison analyses relying on feature extraction. These findings demonstrate the potential of XAI in analyzing neural dynamics in neurodegenerative disorders such as PD, suggesting that the integration of graphene-based electrodes with advanced deep learning models offers a promising solution for real-time PD monitoring and therapy.

We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solving geometry problems, their ability to recognize geometric features remains insufficiently analyzed. To address this gap, we propose a benchmark that evaluates the recognition of visual geometric features, including primitives such as dots and lines, and relations such as orthogonality. Our preliminary study shows that vision encoders often used in general-purpose VLMs, e.g., OpenCLIP, fail to detect these features and struggle to generalize across domains. We develop GeoCLIP, a CLIP based model trained on synthetic geometric diagram-caption pairs to overcome the limitation. Benchmark results show that GeoCLIP outperforms existing vision encoders in recognizing geometric features. We then propose our VLM, GeoDANO, which augments GeoCLIP with a domain adaptation strategy for unseen diagram styles. GeoDANO outperforms specialized methods for plane geometry problems and GPT-4o on MathVerse., Comment: 14 pages, 7 figures, 5 tables

Quantum computing QC emulation is crucial for advancing QC applications, especially given the scalability constraints of current devices. FPGA-based designs offer an efficient and scalable alternative to traditional large-scale platforms, but most are tightly integrated with high-performance systems, limiting their use in mobile and edge environments. This study introduces a compact, standalone FPGA-based QC emulator designed for embedded systems, leveraging the Quantum Approximate Optimization Algorithm (QAOA) to solve the Weighted-MaxCut problem. By restructuring QAOA operations for hardware compatibility, the proposed design reduces time complexity from O(N^2) to O(N), where N equals 2^n for n qubits. This reduction, coupled with a pipeline architecture, significantly minimizes resource consumption, enabling support for up to nine qubits on mid-tier FPGAs, roughly three times more than comparable designs. Additionally, the emulator achieved energy savings ranging from 1.53 times for two-qubit configurations to up to 852 times for nine-qubit configurations, compared to software-based QAOA on embedded processors. These results highlight the practical scalability and resource efficiency of the proposed design, providing a robust foundation for QC emulation in resource-constrained edge devices., Comment: 9 pages, 6 figures, 3 tables

Utilizing 4.5 $fb^-$ of $e^+e^-$ annihilation data collected at center-of-mass energies ranging from 4599.53 MeV to 4698.82 MeV by the BESIII detector at the BEPCII collider, we search for the singly Cabibbo-suppressed hadronic decays $\Lambda_{c}^{+}\to\Sigma^{0} K^{+}\pi^{0}$ and $\Lambda_{c}^{+}\to\Sigma^{0}K^{+}\pi^+\pi^-$ with a single-tag method. No significant signals are observed for both decays. The upper limits on the branching fractions at the $90\%$ confidence level are determined to be $5.0\times 10^{-4}$ for $\Lambda_{c}^{+}\to\Sigma^{0} K^{+}\pi^{0}$ and $6.5\times 10^{-4}$ for $\Lambda_c^{+}\to\Sigma^0K^{+}\pi^{+}\pi^{-}$., Comment: 12 pages, 6 figures

By applying the new supersymmetric localization principle introduced in \cite{Choi:2021yuz,Choi:2023pjn}, we present two complementary approaches for the path integral derivation of the `non-chiral' trace formula for a semisimple compact Lie group $G$, which generalizes the so-called Frenkel trace formula. Corresponding physical systems for each picture are the quantum mechanical sigma model on $G$ and the gauged sigma model on $G\times G$, and the approaches closely follow the spirit of the Eskin trace formula \cite{Choi:2021yuz} and the Selberg trace formula \cite{Choi:2023pjn} respectively. These methods provide a natural conceptual bridge between two seemingly independent derivations in \cite{Choi:2021yuz} and \cite{Choi:2023pjn}., Comment: 13 pages

Facial expression recognition (FER) remains a challenging task due to label ambiguity caused by the subjective nature of facial expressions and noisy samples. Additionally, class imbalance, which is common in real-world datasets, further complicates FER. Although many studies have shown impressive improvements, they typically address only one of these issues, leading to suboptimal results. To tackle both challenges simultaneously, we propose a novel framework called Navigating Label Ambiguity (NLA), which is robust under real-world conditions. The motivation behind NLA is that dynamically estimating and emphasizing ambiguous samples at each iteration helps mitigate noise and class imbalance by reducing the model's bias toward majority classes. To achieve this, NLA consists of two main components: Noise-aware Adaptive Weighting (NAW) and consistency regularization. Specifically, NAW adaptively assigns higher importance to ambiguous samples and lower importance to noisy ones, based on the correlation between the intermediate prediction scores for the ground truth and the nearest negative. Moreover, we incorporate a regularization term to ensure consistent latent distributions. Consequently, NLA enables the model to progressively focus on more challenging ambiguous samples, which primarily belong to the minority class, in the later stages of training. Extensive experiments demonstrate that NLA outperforms existing methods in both overall and mean accuracy, confirming its robustness against noise and class imbalance. To the best of our knowledge, this is the first framework to address both problems simultaneously., Comment: Accepted by AAAI2025

Using data samples of 102 million Upsilon(1S) events and 158 million Upsilon(2S) events collected by the Belle detector at the KEKB asymmetric-energy $e^+e^-$ collider, we search for [udsccbar] pentaquark states decaying to Jpsi Lambda. Using the first observations of Upsilon(1S, 2S) inclusive decays to Jpsi Lambda, we find evidence of the P_ccbars(4459)0 state with a significance of 3.3 standard deviations, including statistical and systematic uncertainties. We measure the mass and width of the Pccbars(4459)0 to be (4471.7 +- 4.8 +- 0.6) MeV/c2 and (21.9 +- 13.1 +- 2.7) MeV, respectively. The branching fractions for P_ccbars(4459)0 production are measured to be B[Upsilon(1S) -> P_ccbars(4459)0/ Pbar_ccbars(4459)0 + anything] = (3.5 +- 2.0 +- 0.2)*10-6 and B[Upsilin(2S) -> P_ccbars(4459)0/ Pbar_ccbars(4459)0 +anything] = (2.9 +- 1.7 +- 0.4)*10-6. The inclusive branching fractions of Upsilon(1S, 2S) -> Jpsi Lambda/Lambdabar are measured to be B[Upsilin(1S) -> Jpsi Lambda/Lambdabar + anything] = (36.9 +- 5.3 +- 2.4)*10-6 and B[Upsilon(2S) -> Jpsi Lambda/Lambdabar + anything] = (22.3 +- 5.7 +- 3.1)*10-6. We measure the visible cross section $\sigma(e^+e^- \to J/psi \Lambda/\bar\Lambda$ + anything) = (90 +- 14 +- 6) fb for the continuum production at $\sqrt{s} = 10.52$ GeV. In all cases, the first uncertainties are statistical and the second are systematic., Comment: 8 pages, 3 figures

This paper addresses the challenge of channel estimation in extremely large-scale multiple-input multiple-output (XL-MIMO) systems, pivotal for the advancement of 6G communications. XL-MIMO systems, characterized by their vast antenna arrays, necessitate accurate channel state information (CSI) to leverage high spatial multiplexing and beamforming gains. However, conventional channel estimation methods for near-field XL-MIMO encounter significant computational complexity due to the exceedingly high parameter quantization levels needed for estimating the parametric near-field channel. To address this, we propose a low-complexity two-stage on-grid channel estimation algorithm designed for near-field XL-MIMO systems. The first stage focuses on estimating the LoS channel component while treating the NLoS paths as interference. This estimation is accomplished through an alternating subarray-wise array gain maximization (ASAGM) approach based on the piecewise outer product model (SOPM). In the second stage, we estimate the NLoS channel component by utilizing the sensing matrix refinement-based orthogonal matching pursuit (SMR-OMP) algorithm. This approach helps reduce the high computational complexity associated with large-dimensional joint sensing matrices. Simulation results demonstrate the effectiveness of our proposed low-complexity method, showcasing its significant superiority over existing near-field XL-MIMO channel estimation techniques, particularly in intermediate and high SNR regimes, and in practical scenarios involving arbitrary array placements.

Many-body hydrodynamic interactions (HIs) play an important role in the dynamics of fluid suspensions. While many-body HIs have been studied extensively using particle simulations, there is a dearth of experimental frameworks with which to quantify fluid-mediated multi-body interactions. To address this, we design an experimental method that utilizes optical laser tweezers for quantifying fluid-mediated colloidal interactions with exquisite precision and control. By inducing translation-rotation hydrodynamic coupling between trapped fluorescently-labeled colloids, we obtain a direct reporter of few- to many-body HIs experimentally. We leverage the torque-free nature of laser tweezers to enable sensitive measurements of signals between trapped colloids. First, we measure the pair HI between a stationary tracer probe and a translating particle as a function of their separation distance. We discover that our technique can precisely quantify distant fluid disturbances that are generated by ~2 pN of hydrodynamic force at 12 particle radii of separation. To study the effect of many-body HIs, we measure the rotational mobility of a probe in a three-particle setup and in a model material, a two-dimensional hexagonally-close-packed lattice, that undergoes oscillatory strain. Respectively, we discover that the probe's rotation can reverse in certain three-body configurations, and we find that rotational mobility in the crystalline array is strongly attenuated by particle rigidity. Experimental measurements are corroborated by microhydrodynamic theory and Stokesian Dynamics simulations with excellent agreement, highlighting our ability to measure accurately many-body HIs. Lastly, we extend our theoretical framework to manipulate colloidal-scale fluid flows. With experimental validation, we compute the required trajectory of a moving particle to induce a desired angular velocity of a probe.

Time-series forecasting research has converged to a small set of datasets and a standardized collection of evaluation scenarios. Such a standardization is to a specific extent needed for comparable research. However, the underlying assumption is, that the considered setting is a representative for the problem as a whole. In this paper, we challenge this assumption and show that the current scenario gives a strongly biased perspective on the state of time-series forecasting research. To be more detailed, we show that the current evaluation scenario is heavily biased by the simplicity of the current datasets. We furthermore emphasize, that when the lookback-window is properly tuned, current models usually do not need any information flow across channels. However, when using more complex benchmark data, the situation changes: Here, modeling channel-interactions in a sophisticated manner indeed enhances performances. Furthermore, in this complex evaluation scenario, Crossformer, a method regularly neglected as an important baseline, is the SOTA method for time series forecasting. Based on this, we present the Fast Channel-dependent Transformer (FaCT), a simplified version of Crossformer which closes the runtime gap between Crossformer and TimeMixer, leading to an efficient model for complex forecasting datasets.

The observation of neutrino oscillations has established that neutrinos have non-zero masses. This phenomenon is not explained by the Standard Model of particle physics, but one viable explanation to this dilemma involves the existence of heavy neutral leptons in the form of right-handed neutrinos. This work presents the first search for heavy neutral leptons with the IceCube Neutrino Observatory. The standard three flavor neutrino model is extended by adding a fourth GeV-scale mass state allowing mixing with the $\tau$ sector through the parameter $|U_{\tau4}|^2$. The analysis is performed by searching for signatures of heavy neutral leptons that are directly produced via up-scattering of atmospheric $\nu_\tau$'s inside the IceCube detection volume. Three heavy neutral lepton mass values, $m_4$, of 0.3 GeV, 0.6 GeV, and 1.0 GeV are tested using ten years of data, collected between 2011 and 2021. No significant signal of heavy neutral leptons is observed for any of the tested masses. The resulting constraints for the mixing parameter are $|U_{\tau4}|^2 < 0.19$ ($m_4 = 0.3$ GeV), $|U_{\tau4}|^2 < 0.36$ ($m_4 = 0.6$ GeV), and $|U_{\tau4}|^2 < 0.40$ ($m_4 = 1.0$ GeV) at the 90% confidence level. This analysis serves as proof-of-concept for heavy neutral lepton searches in IceCube. The heavy neutral lepton event generator, developed in this work, and the analysis of the expected signatures lay the fundamental groundwork for future searches thereof.

Blockchain, often integrated with distributed systems and security enhancements, has significant potential in various industries. However, environmental concerns and the efficiency of consortia-controlled permissioned networks remain critical issues. We use a Stochastic Petri Net model to analyze transaction flows in Hyperledger Fabric networks, achieving a 95% confidence interval for response times. This model enables administrators to assess the impact of system changes on resource utilization. Sensitivity analysis reveals major factors influencing response times and throughput. Our case studies demonstrate that block size can alter throughput and response times by up to 200%, underscoring the need for performance optimization with resource efficiency.

Group recommendation aims at providing optimized recommendations tailored to diverse groups, enabling groups to enjoy appropriate items. On the other hand, most existing group recommendation methods are built upon deep neural network (DNN) architectures designed to capture the intricate relationships between member-level and group-level interactions. While these DNN-based approaches have proven their effectiveness, they require complex and expensive training procedures to incorporate group-level interactions in addition to member-level interactions. To overcome such limitations, we introduce Group-GF, a new approach for extremely fast recommendations of items to each group via multi-view graph filtering (GF) that offers a holistic view of complex member-group dynamics, without the need for costly model training. Specifically, in Group-GF, we first construct three item similarity graphs manifesting different viewpoints for GF. Then, we discover a distinct polynomial graph filter for each similarity graph and judiciously aggregate the three graph filters. Extensive experiments demonstrate the effectiveness of Group-GF in terms of significantly reducing runtime and achieving state-of-the-art recommendation accuracy., Comment: 5 pages, 3 figures, 4 tables; ACM Web Conference (WWW 2025) (to appear) (Please cite our conference version.)

By analyzing a $\psi(3686)$ data sample containing $(107.7\pm0.6)\times10^{6}$ events taken with the BESIII detector at the BEPCII storage ring in 2009, the $\chi_{c0}$ resonance parameters are precisely measured using $\chi_{c0,c2} \to \pi^+\pi^-/K^+K^-$ events. The mass of $\chi_{c0}$ is determined to be $M(\chi_{c0})=(3415.67\pm0.07\pm0.06\pm0.07$)~MeV/$c^2$, and its full width is $\Gamma(\chi_{c0})=(12.44\pm0.12\pm0.12)~{\rm MeV}$, where the first uncertainty is statistical, the second systematic, and the third for mass comes from $\chi_{c2}$ mass uncertainty. These measurements improve the precision of $\chi_{c0}$ mass by a factor of four and width by one order of magnitude over the previous individual measurements, and significantly boost our knowledge about the charmonium spectrum. Together with additional $(345.4\pm2.6)\times10^{6}$ $\psi(3686)$ data events taken in 2012, the decay branching fractions of $\chi_{c0,c2}\to\pi^+\pi^-/K^+K^-$ are measured as well, with precision improved by a factor of three compared to previous measurements. These $\chi_{c0}$ decay branching fractions provide important inputs for the study of glueballs., Comment: 9 pages, 1 figure

The promise of quantum computation is contingent upon physical qubits with both low gate error rate and broad scalability. Silicon-based spins are a leading qubit platform, but demonstrations to date have not utilized fabrication processes capable of extending arrays in two dimensions while maintaining complete control of individual spins. Here, we implement an interconnect process, common in semiconductor manufacturing, with multiple back-end-of-line layers to show an extendable two-dimensional array of spins with fully controllable nearest-neighbor exchange interactions. In a device using three interconnect layers, we encode exchange-only qubits and achieve average single-qubit gate fidelities consistent with single-layer devices, including fidelities greater than 99.9%, as measured by blind randomized benchmarking. Moreover, with spin connectivity in two dimensions, we show that both linear and right-angle exchange-only qubits with high performance can be formed, enabling qubit array reconfigurability in the presence of defects. This extendable device platform demonstrates that industrial manufacturing techniques can be leveraged for scalable spin qubit technologies.

Hyperledger Fabric stands as a leading framework for permissioned blockchain systems, ensuring data security and auditability for enterprise applications. As applications on this platform grow, understanding its complex configuration concerning various blockchain parameters becomes vital. These configurations significantly affect the system's performance and cost. In this research, we introduce a Stochastic Petri Net (SPN) model to analyze Hyperledger Fabric's performance, considering variations in blockchain parameters, computational resources, and transaction rates. We provide case studies to validate the utility of our model, aiding blockchain administrators in determining optimal configurations for their applications. A key observation from our model highlights the block size's role in system response time. We noted an increased mean response time, between 1 to 25 seconds, due to variations in transaction arrival rates.

Recent advances in large language models (LLMs) have shown promising improvements, often surpassing existing methods across a wide range of downstream tasks in natural language processing. However, these models still face challenges, which may hinder their practical applicability. For example, the phenomenon of hallucination is known to compromise the reliability of LLMs, especially in fields that demand high factual precision. Current benchmarks primarily focus on hallucination detection and factuality evaluation but do not extend beyond identification. This paper proposes an explanation enhanced hallucination-detection model, coined as HuDEx, aimed at enhancing the reliability of LLM-generated responses by both detecting hallucinations and providing detailed explanations. The proposed model provides a novel approach to integrate detection with explanations, and enable both users and the LLM itself to understand and reduce errors. Our measurement results demonstrate that the proposed model surpasses larger LLMs, such as Llama3 70B and GPT-4, in hallucination detection accuracy, while maintaining reliable explanations. Furthermore, the proposed model performs well in both zero-shot and other test environments, showcasing its adaptability across diverse benchmark datasets. The proposed approach further enhances the hallucination detection research by introducing a novel approach to integrating interpretability with hallucination detection, which further enhances the performance and reliability of evaluating hallucinations in language models., Comment: 11 pages

Federated Learning (FL) enables collaborative model training while keeping client data private. However, exposing individual client updates makes FL vulnerable to reconstruction attacks. Secure aggregation mitigates such privacy risks but prevents the server from verifying the validity of each client update, creating a privacy-robustness tradeoff. Recent efforts attempt to address this tradeoff by enforcing checks on client updates using zero-knowledge proofs, but they support limited predicates and often depend on public validation data. We propose SLVR, a general framework that securely leverages clients' private data through secure multi-party computation. By utilizing clients' data, SLVR not only eliminates the need for public validation data, but also enables a wider range of checks for robustness, including cross-client accuracy validation. It also adapts naturally to distribution shifts in client data as it can securely refresh its validation data up-to-date. Our empirical evaluations show that SLVR improves robustness against model poisoning attacks, particularly outperforming existing methods by up to 50% under adaptive attacks. Additionally, SLVR demonstrates effective adaptability and stable convergence under various distribution shift scenarios., Comment: 29 pages

Adaptation is to make model learn the patterns shifted from the training distribution. In general, this adaptation is formulated as the minimum entropy problem. However, the minimum entropy problem has inherent limitation -- shifted initialization cascade phenomenon. We extend the relationship between the minimum entropy problem and the minimum set cover problem via Lebesgue integral. This extension reveals that internal mechanism of the minimum entropy problem ignores the relationship between disentangled representations, which leads to shifted initialization cascade. From the analysis, we introduce a new clustering algorithm, Union-find based Recursive Clustering Algorithm~(URECA). URECA is an efficient clustering algorithm for the leverage of the relationships between disentangled representations. The update rule of URECA depends on Thresholdly-Updatable Stationary Assumption to dynamics as a released version of Stationary Assumption. This assumption helps URECA to transport disentangled representations with no errors based on the relationships between disentangled representations. URECA also utilize simulation trick to efficiently cluster disentangled representations. The wide range of evaluations show that URECA achieves consistent performance gains for the few-shot adaptation to diverse types of shifts along with advancement to State-of-The-Art performance in CoSQA in the scenario of query shift.